korg/linux
0
0
Fork 0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2024-11-11 21:38:32 +08:00
Code Issues Packages Projects Releases Wiki Activity

bpf-next-for-netdev

Browse Source 
-----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQTFp0I1jqZrAX+hPRXbK58LschIgwUCZYHIBwAKCRDbK58LschI
 g7nvAQDM5/5vMbsO9rEJAdHomJ4Ybvcv/2SG652za9DVEu6VUgD+JCLJ9He/hMx2
 1wZ3wcjwxibNAZ/cZp6yu1JpOtR3rQo=
 =BO/b
 -----END PGP SIGNATURE-----

Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2023-12-19

Hi David, hi Jakub, hi Paolo, hi Eric,

The following pull-request contains BPF updates for your *net-next* tree.

We've added 2 non-merge commits during the last 1 day(s) which contain
a total of 40 files changed, 642 insertions(+), 2926 deletions(-).

The main changes are:

1) Revert all of BPF token-related patches for now as per list discussion [0],
   from Andrii Nakryiko.

   [0] https://lore.kernel.org/bpf/CAHk-=wg7JuFYwGy=GOMbRCtOL+jwSQsdUaBsRWkDVYbxipbM5A@mail.gmail.com

2) Fix a syzbot-reported use-after-free read in nla_find() triggered from
   bpf_skb_get_nlattr_nest() helper, from Jakub Kicinski.

bpf-next-for-netdev

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next:
  Revert BPF token-related functionality
  bpf: Use nla_ok() instead of checking nla_len directly
====================

Link: https://lore.kernel.org/r/20231219170359.11035-1-daniel@iogearbox.net
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
This commit is contained in:
Paolo Abeni 2023-12-19 18:35:28 +01:00
commit 1728df7fc1
40 changed files with 641 additions and 2925 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
drivers/media/rc/bpf-lirc.c
View File

@ -110,7 +110,7 @@ lirc_mode2_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_get_prandom_u32:
return &bpf_get_prandom_u32_proto;
case BPF_FUNC_trace_printk:
if (bpf_token_capable(prog->aux->token, CAP_PERFMON))
if (perfmon_capable())
return bpf_get_trace_printk_proto();
fallthrough;
default:

85
include/linux/bpf.h
View File

@ -52,10 +52,6 @@ struct module;
struct bpf_func_state;
struct ftrace_ops;
struct cgroup;
struct bpf_token;
struct user_namespace;
struct super_block;
struct inode;
extern struct idr btf_idr;
extern spinlock_t btf_idr_lock;
@ -1488,7 +1484,6 @@ struct bpf_prog_aux {
#ifdef CONFIG_SECURITY
void *security;
#endif
struct bpf_token *token;
struct bpf_prog_offload *offload;
struct btf *btf;
struct bpf_func_info *func_info;
@ -1613,31 +1608,6 @@ struct bpf_link_primer {
u32 id;
};
struct bpf_mount_opts {
kuid_t uid;
kgid_t gid;
umode_t mode;
/* BPF token-related delegation options */
u64 delegate_cmds;
u64 delegate_maps;
u64 delegate_progs;
u64 delegate_attachs;
};
struct bpf_token {
struct work_struct work;
atomic64_t refcnt;
struct user_namespace *userns;
u64 allowed_cmds;
u64 allowed_maps;
u64 allowed_progs;
u64 allowed_attachs;
#ifdef CONFIG_SECURITY
void *security;
#endif
};
struct bpf_struct_ops_value;
struct btf_member;
@ -2097,7 +2067,6 @@ static inline void bpf_enable_instrumentation(void)
migrate_enable();
}
extern const struct super_operations bpf_super_ops;
extern const struct file_operations bpf_map_fops;
extern const struct file_operations bpf_prog_fops;
extern const struct file_operations bpf_iter_fops;
@ -2232,26 +2201,24 @@ static inline void bpf_map_dec_elem_count(struct bpf_map *map)
extern int sysctl_unprivileged_bpf_disabled;
bool bpf_token_capable(const struct bpf_token *token, int cap);
static inline bool bpf_allow_ptr_leaks(const struct bpf_token *token)
static inline bool bpf_allow_ptr_leaks(void)
{
return bpf_token_capable(token, CAP_PERFMON);
return perfmon_capable();
}
static inline bool bpf_allow_uninit_stack(const struct bpf_token *token)
static inline bool bpf_allow_uninit_stack(void)
{
return bpf_token_capable(token, CAP_PERFMON);
return perfmon_capable();
}
static inline bool bpf_bypass_spec_v1(const struct bpf_token *token)
static inline bool bpf_bypass_spec_v1(void)
{
return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON);
return cpu_mitigations_off() || perfmon_capable();
}
static inline bool bpf_bypass_spec_v4(const struct bpf_token *token)
static inline bool bpf_bypass_spec_v4(void)
{
return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON);
return cpu_mitigations_off() || perfmon_capable();
}
int bpf_map_new_fd(struct bpf_map *map, int flags);
@ -2268,21 +2235,8 @@ int bpf_link_new_fd(struct bpf_link *link);
struct bpf_link *bpf_link_get_from_fd(u32 ufd);
struct bpf_link *bpf_link_get_curr_or_next(u32 *id);
void bpf_token_inc(struct bpf_token *token);
void bpf_token_put(struct bpf_token *token);
int bpf_token_create(union bpf_attr *attr);
struct bpf_token *bpf_token_get_from_fd(u32 ufd);
bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd);
bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type);
bool bpf_token_allow_prog_type(const struct bpf_token *token,
enum bpf_prog_type prog_type,
enum bpf_attach_type attach_type);
int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname);
int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags);
struct inode *bpf_get_inode(struct super_block *sb, const struct inode *dir,
umode_t mode);
#define BPF_ITER_FUNC_PREFIX "bpf_iter_"
#define DEFINE_BPF_ITER_FUNC(target, args...) \
@ -2526,8 +2480,7 @@ const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type
struct bpf_prog *bpf_prog_by_id(u32 id);
struct bpf_link *bpf_link_by_id(u32 id);
const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id,
const struct bpf_prog *prog);
const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id);
void bpf_task_storage_free(struct task_struct *task);
void bpf_cgrp_storage_free(struct cgroup *cgroup);
bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog);
@ -2646,24 +2599,6 @@ static inline int bpf_obj_get_user(const char __user *pathname, int flags)
return -EOPNOTSUPP;
}
static inline bool bpf_token_capable(const struct bpf_token *token, int cap)
{
return capable(cap) || (cap != CAP_SYS_ADMIN && capable(CAP_SYS_ADMIN));
}
static inline void bpf_token_inc(struct bpf_token *token)
{
}
static inline void bpf_token_put(struct bpf_token *token)
{
}
static inline struct bpf_token *bpf_token_get_from_fd(u32 ufd)
{
return ERR_PTR(-EOPNOTSUPP);
}
static inline void __dev_flush(void)
{
}
@ -2787,7 +2722,7 @@ static inline int btf_struct_access(struct bpf_verifier_log *log,
}
static inline const struct bpf_func_proto *
bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
bpf_base_func_proto(enum bpf_func_id func_id)
{
return NULL;
}

2
include/linux/filter.h
View File

@ -1139,7 +1139,7 @@ static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog)
return false;
if (!bpf_jit_harden)
return false;
if (bpf_jit_harden == 1 && bpf_token_capable(prog->aux->token, CAP_BPF))
if (bpf_jit_harden == 1 && bpf_capable())
return false;
return true;

15
include/linux/lsm_hook_defs.h
View File

@ -398,17 +398,10 @@ LSM_HOOK(void, LSM_RET_VOID, audit_rule_free, void *lsmrule)
LSM_HOOK(int, 0, bpf, int cmd, union bpf_attr *attr, unsigned int size)
LSM_HOOK(int, 0, bpf_map, struct bpf_map *map, fmode_t fmode)
LSM_HOOK(int, 0, bpf_prog, struct bpf_prog *prog)
LSM_HOOK(int, 0, bpf_map_create, struct bpf_map *map, union bpf_attr *attr,
struct bpf_token *token)
LSM_HOOK(void, LSM_RET_VOID, bpf_map_free, struct bpf_map *map)
LSM_HOOK(int, 0, bpf_prog_load, struct bpf_prog *prog, union bpf_attr *attr,
struct bpf_token *token)
LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free, struct bpf_prog *prog)
LSM_HOOK(int, 0, bpf_token_create, struct bpf_token *token, union bpf_attr *attr,
struct path *path)
LSM_HOOK(void, LSM_RET_VOID, bpf_token_free, struct bpf_token *token)
LSM_HOOK(int, 0, bpf_token_cmd, const struct bpf_token *token, enum bpf_cmd cmd)
LSM_HOOK(int, 0, bpf_token_capable, const struct bpf_token *token, int cap)
LSM_HOOK(int, 0, bpf_map_alloc_security, struct bpf_map *map)
LSM_HOOK(void, LSM_RET_VOID, bpf_map_free_security, struct bpf_map *map)
LSM_HOOK(int, 0, bpf_prog_alloc_security, struct bpf_prog_aux *aux)
LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free_security, struct bpf_prog_aux *aux)
#endif /* CONFIG_BPF_SYSCALL */
LSM_HOOK(int, 0, locked_down, enum lockdown_reason what)

43
include/linux/security.h
View File

@ -32,7 +32,6 @@
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/sockptr.h>
#include <linux/bpf.h>
struct linux_binprm;
struct cred;
@ -2021,22 +2020,15 @@ static inline void securityfs_remove(struct dentry *dentry)
union bpf_attr;
struct bpf_map;
struct bpf_prog;
struct bpf_token;
struct bpf_prog_aux;
#ifdef CONFIG_SECURITY
extern int security_bpf(int cmd, union bpf_attr *attr, unsigned int size);
extern int security_bpf_map(struct bpf_map *map, fmode_t fmode);
extern int security_bpf_prog(struct bpf_prog *prog);
extern int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr,
struct bpf_token *token);
extern int security_bpf_map_alloc(struct bpf_map *map);
extern void security_bpf_map_free(struct bpf_map *map);
extern int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr,
struct bpf_token *token);
extern void security_bpf_prog_free(struct bpf_prog *prog);
extern int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr,
struct path *path);
extern void security_bpf_token_free(struct bpf_token *token);
extern int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd);
extern int security_bpf_token_capable(const struct bpf_token *token, int cap);
extern int security_bpf_prog_alloc(struct bpf_prog_aux *aux);
extern void security_bpf_prog_free(struct bpf_prog_aux *aux);
#else
static inline int security_bpf(int cmd, union bpf_attr *attr,
unsigned int size)
@ -2054,8 +2046,7 @@ static inline int security_bpf_prog(struct bpf_prog *prog)
return 0;
}
static inline int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr,
struct bpf_token *token)
static inline int security_bpf_map_alloc(struct bpf_map *map)
{
return 0;
}
@ -2063,33 +2054,13 @@ static inline int security_bpf_map_create(struct bpf_map *map, union bpf_attr *a
static inline void security_bpf_map_free(struct bpf_map *map)
{ }
static inline int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr,
struct bpf_token *token)
static inline int security_bpf_prog_alloc(struct bpf_prog_aux *aux)
{
return 0;
}
static inline void security_bpf_prog_free(struct bpf_prog *prog)
static inline void security_bpf_prog_free(struct bpf_prog_aux *aux)
{ }
static inline int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr,
struct path *path)
{
return 0;
}
static inline void security_bpf_token_free(struct bpf_token *token)
{ }
static inline int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd)
{
return 0;
}
static inline int security_bpf_token_capable(const struct bpf_token *token, int cap)
{
return 0;
}
#endif /* CONFIG_SECURITY */
#endif /* CONFIG_BPF_SYSCALL */

42
include/uapi/linux/bpf.h
View File

@ -847,36 +847,6 @@ union bpf_iter_link_info {
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*
* BPF_TOKEN_CREATE
* Description
* Create BPF token with embedded information about what
* BPF-related functionality it allows:
* - a set of allowed bpf() syscall commands;
* - a set of allowed BPF map types to be created with
* BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed;
* - a set of allowed BPF program types and BPF program attach
* types to be loaded with BPF_PROG_LOAD command, if
* BPF_PROG_LOAD itself is allowed.
*
* BPF token is created (derived) from an instance of BPF FS,
* assuming it has necessary delegation mount options specified.
* This BPF token can be passed as an extra parameter to various
* bpf() syscall commands to grant BPF subsystem functionality to
* unprivileged processes.
*
* When created, BPF token is "associated" with the owning
* user namespace of BPF FS instance (super block) that it was
* derived from, and subsequent BPF operations performed with
* BPF token would be performing capabilities checks (i.e.,
* CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within
* that user namespace. Without BPF token, such capabilities
* have to be granted in init user namespace, making bpf()
* syscall incompatible with user namespace, for the most part.
*
* Return
* A new file descriptor (a nonnegative integer), or -1 if an
* error occurred (in which case, *errno* is set appropriately).
*
* NOTES
* eBPF objects (maps and programs) can be shared between processes.
*
@ -931,8 +901,6 @@ enum bpf_cmd {
BPF_ITER_CREATE,
BPF_LINK_DETACH,
BPF_PROG_BIND_MAP,
BPF_TOKEN_CREATE,
__MAX_BPF_CMD,
};
enum bpf_map_type {
@ -983,7 +951,6 @@ enum bpf_map_type {
BPF_MAP_TYPE_BLOOM_FILTER,
BPF_MAP_TYPE_USER_RINGBUF,
BPF_MAP_TYPE_CGRP_STORAGE,
__MAX_BPF_MAP_TYPE
};
/* Note that tracing related programs such as
@ -1028,7 +995,6 @@ enum bpf_prog_type {
BPF_PROG_TYPE_SK_LOOKUP,
BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */
BPF_PROG_TYPE_NETFILTER,
__MAX_BPF_PROG_TYPE
};
enum bpf_attach_type {
@ -1437,7 +1403,6 @@ union bpf_attr {
* to using 5 hash functions).
*/
__u64 map_extra;
__u32 map_token_fd;
};
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@ -1507,7 +1472,6 @@ union bpf_attr {
* truncated), or smaller (if log buffer wasn't filled completely).
*/
__u32 log_true_size;
__u32 prog_token_fd;
};
struct { /* anonymous struct used by BPF_OBJ_* commands */
@ -1620,7 +1584,6 @@ union bpf_attr {
* truncated), or smaller (if log buffer wasn't filled completely).
*/
__u32 btf_log_true_size;
__u32 btf_token_fd;
};
struct {
@ -1751,11 +1714,6 @@ union bpf_attr {
__u32 flags; /* extra flags */
} prog_bind_map;
struct { /* struct used by BPF_TOKEN_CREATE command */
__u32 flags;
__u32 bpffs_fd;
} token_create;
} __attribute__((aligned(8)));
/* The description below is an attempt at providing documentation to eBPF

2
kernel/bpf/Makefile
View File

@ -6,7 +6,7 @@ cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse
endif
CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy)
obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o token.o
obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o
obj-$(CONFIG_BPF_SYSCALL) += bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o
obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o
obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o

2
kernel/bpf/arraymap.c
View File

@ -82,7 +82,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
int numa_node = bpf_map_attr_numa_node(attr);
u32 elem_size, index_mask, max_entries;
bool bypass_spec_v1 = bpf_bypass_spec_v1(NULL);
bool bypass_spec_v1 = bpf_bypass_spec_v1();
u64 array_size, mask64;
struct bpf_array *array;

15
kernel/bpf/bpf_lsm.c
View File

@ -260,15 +260,9 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
BTF_SET_START(sleepable_lsm_hooks)
BTF_ID(func, bpf_lsm_bpf)
BTF_ID(func, bpf_lsm_bpf_map)
BTF_ID(func, bpf_lsm_bpf_map_create)
BTF_ID(func, bpf_lsm_bpf_map_free)
BTF_ID(func, bpf_lsm_bpf_map_alloc_security)
BTF_ID(func, bpf_lsm_bpf_map_free_security)
BTF_ID(func, bpf_lsm_bpf_prog)
BTF_ID(func, bpf_lsm_bpf_prog_load)
BTF_ID(func, bpf_lsm_bpf_prog_free)
BTF_ID(func, bpf_lsm_bpf_token_create)
BTF_ID(func, bpf_lsm_bpf_token_free)
BTF_ID(func, bpf_lsm_bpf_token_cmd)
BTF_ID(func, bpf_lsm_bpf_token_capable)
BTF_ID(func, bpf_lsm_bprm_check_security)
BTF_ID(func, bpf_lsm_bprm_committed_creds)
BTF_ID(func, bpf_lsm_bprm_committing_creds)
@ -363,8 +357,9 @@ BTF_ID(func, bpf_lsm_userns_create)
BTF_SET_END(sleepable_lsm_hooks)
BTF_SET_START(untrusted_lsm_hooks)
BTF_ID(func, bpf_lsm_bpf_map_free)
BTF_ID(func, bpf_lsm_bpf_prog_free)
BTF_ID(func, bpf_lsm_bpf_map_free_security)
BTF_ID(func, bpf_lsm_bpf_prog_alloc_security)
BTF_ID(func, bpf_lsm_bpf_prog_free_security)
BTF_ID(func, bpf_lsm_file_alloc_security)
BTF_ID(func, bpf_lsm_file_free_security)
#ifdef CONFIG_SECURITY_NETWORK

6
kernel/bpf/cgroup.c
View File

@ -1630,7 +1630,7 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_perf_event_output:
return &bpf_event_output_data_proto;
default:
return bpf_base_func_proto(func_id, prog);
return bpf_base_func_proto(func_id);
}
}
@ -2191,7 +2191,7 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_perf_event_output:
return &bpf_event_output_data_proto;
default:
return bpf_base_func_proto(func_id, prog);
return bpf_base_func_proto(func_id);
}
}
@ -2348,7 +2348,7 @@ cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_perf_event_output:
return &bpf_event_output_data_proto;
default:
return bpf_base_func_proto(func_id, prog);
return bpf_base_func_proto(func_id);
}
}

3
kernel/bpf/core.c
View File

@ -682,7 +682,7 @@ static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp)
void bpf_prog_kallsyms_add(struct bpf_prog *fp)
{
if (!bpf_prog_kallsyms_candidate(fp) ||
!bpf_token_capable(fp->aux->token, CAP_BPF))
!bpf_capable())
return;
bpf_prog_ksym_set_addr(fp);
@ -2779,7 +2779,6 @@ void bpf_prog_free(struct bpf_prog *fp)
if (aux->dst_prog)
bpf_prog_put(aux->dst_prog);
bpf_token_put(aux->token);
INIT_WORK(&aux->work, bpf_prog_free_deferred);
schedule_work(&aux->work);
}

6
kernel/bpf/helpers.c
View File

@ -1679,7 +1679,7 @@ const struct bpf_func_proto bpf_probe_read_kernel_str_proto __weak;
const struct bpf_func_proto bpf_task_pt_regs_proto __weak;
const struct bpf_func_proto *
bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
bpf_base_func_proto(enum bpf_func_id func_id)
{
switch (func_id) {
case BPF_FUNC_map_lookup_elem:
@ -1730,7 +1730,7 @@ bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
break;
}
if (!bpf_token_capable(prog->aux->token, CAP_BPF))
if (!bpf_capable())
return NULL;
switch (func_id) {
@ -1788,7 +1788,7 @@ bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
break;
}
if (!bpf_token_capable(prog->aux->token, CAP_PERFMON))
if (!perfmon_capable())
return NULL;
switch (func_id) {

324
kernel/bpf/inode.c
View File

@ -20,7 +20,6 @@
#include <linux/filter.h>
#include <linux/bpf.h>
#include <linux/bpf_trace.h>
#include <linux/kstrtox.h>
#include "preload/bpf_preload.h"
enum bpf_type {
@ -99,9 +98,9 @@ static const struct inode_operations bpf_prog_iops = { };
static const struct inode_operations bpf_map_iops = { };
static const struct inode_operations bpf_link_iops = { };
struct inode *bpf_get_inode(struct super_block *sb,
const struct inode *dir,
umode_t mode)
static struct inode *bpf_get_inode(struct super_block *sb,
const struct inode *dir,
umode_t mode)
{
struct inode *inode;
@ -595,183 +594,15 @@ struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type typ
}
EXPORT_SYMBOL(bpf_prog_get_type_path);
struct bpffs_btf_enums {
const struct btf *btf;
const struct btf_type *cmd_t;
const struct btf_type *map_t;
const struct btf_type *prog_t;
const struct btf_type *attach_t;
};
static int find_bpffs_btf_enums(struct bpffs_btf_enums *info)
{
const struct btf *btf;
const struct btf_type *t;
const char *name;
int i, n;
memset(info, 0, sizeof(*info));
btf = bpf_get_btf_vmlinux();
if (IS_ERR(btf))
return PTR_ERR(btf);
if (!btf)
return -ENOENT;
info->btf = btf;
for (i = 1, n = btf_nr_types(btf); i < n; i++) {
t = btf_type_by_id(btf, i);
if (!btf_type_is_enum(t))
continue;
name = btf_name_by_offset(btf, t->name_off);
if (!name)
continue;
if (strcmp(name, "bpf_cmd") == 0)
info->cmd_t = t;
else if (strcmp(name, "bpf_map_type") == 0)
info->map_t = t;
else if (strcmp(name, "bpf_prog_type") == 0)
info->prog_t = t;
else if (strcmp(name, "bpf_attach_type") == 0)
info->attach_t = t;
else
continue;
if (info->cmd_t && info->map_t && info->prog_t && info->attach_t)
return 0;
}
return -ESRCH;
}
static bool find_btf_enum_const(const struct btf *btf, const struct btf_type *enum_t,
const char *prefix, const char *str, int *value)
{
const struct btf_enum *e;
const char *name;
int i, n, pfx_len = strlen(prefix);
*value = 0;
if (!btf || !enum_t)
return false;
for (i = 0, n = btf_vlen(enum_t); i < n; i++) {
e = &btf_enum(enum_t)[i];
name = btf_name_by_offset(btf, e->name_off);
if (!name || strncasecmp(name, prefix, pfx_len) != 0)
continue;
/* match symbolic name case insensitive and ignoring prefix */
if (strcasecmp(name + pfx_len, str) == 0) {
*value = e->val;
return true;
}
}
return false;
}
static void seq_print_delegate_opts(struct seq_file *m,
const char *opt_name,
const struct btf *btf,
const struct btf_type *enum_t,
const char *prefix,
u64 delegate_msk, u64 any_msk)
{
const struct btf_enum *e;
bool first = true;
const char *name;
u64 msk;
int i, n, pfx_len = strlen(prefix);
delegate_msk &= any_msk; /* clear unknown bits */
if (delegate_msk == 0)
return;
seq_printf(m, ",%s", opt_name);
if (delegate_msk == any_msk) {
seq_printf(m, "=any");
return;
}
if (btf && enum_t) {
for (i = 0, n = btf_vlen(enum_t); i < n; i++) {
e = &btf_enum(enum_t)[i];
name = btf_name_by_offset(btf, e->name_off);
if (!name || strncasecmp(name, prefix, pfx_len) != 0)
continue;
msk = 1ULL << e->val;
if (delegate_msk & msk) {
/* emit lower-case name without prefix */
seq_printf(m, "%c", first ? '=' : ':');
name += pfx_len;
while (*name) {
seq_printf(m, "%c", tolower(*name));
name++;
}
delegate_msk &= ~msk;
first = false;
}
}
}
if (delegate_msk)
seq_printf(m, "%c0x%llx", first ? '=' : ':', delegate_msk);
}
/*
* Display the mount options in /proc/mounts.
*/
static int bpf_show_options(struct seq_file *m, struct dentry *root)
{
struct bpf_mount_opts *opts = root->d_sb->s_fs_info;
struct inode *inode = d_inode(root);
umode_t mode = inode->i_mode & S_IALLUGO & ~S_ISVTX;
u64 mask;
umode_t mode = d_inode(root)->i_mode & S_IALLUGO & ~S_ISVTX;
if (!uid_eq(inode->i_uid, GLOBAL_ROOT_UID))
seq_printf(m, ",uid=%u",
from_kuid_munged(&init_user_ns, inode->i_uid));
if (!gid_eq(inode->i_gid, GLOBAL_ROOT_GID))
seq_printf(m, ",gid=%u",
from_kgid_munged(&init_user_ns, inode->i_gid));
if (mode != S_IRWXUGO)
seq_printf(m, ",mode=%o", mode);
if (opts->delegate_cmds || opts->delegate_maps ||
opts->delegate_progs || opts->delegate_attachs) {
struct bpffs_btf_enums info;
/* ignore errors, fallback to hex */
(void)find_bpffs_btf_enums(&info);
mask = (1ULL << __MAX_BPF_CMD) - 1;
seq_print_delegate_opts(m, "delegate_cmds",
info.btf, info.cmd_t, "BPF_",
opts->delegate_cmds, mask);
mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1;
seq_print_delegate_opts(m, "delegate_maps",
info.btf, info.map_t, "BPF_MAP_TYPE_",
opts->delegate_maps, mask);
mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1;
seq_print_delegate_opts(m, "delegate_progs",
info.btf, info.prog_t, "BPF_PROG_TYPE_",
opts->delegate_progs, mask);
mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1;
seq_print_delegate_opts(m, "delegate_attachs",
info.btf, info.attach_t, "BPF_",
opts->delegate_attachs, mask);
}
return 0;
}
@ -786,7 +617,7 @@ static void bpf_free_inode(struct inode *inode)
free_inode_nonrcu(inode);
}
const struct super_operations bpf_super_ops = {
static const struct super_operations bpf_super_ops = {
.statfs = simple_statfs,
.drop_inode = generic_delete_inode,
.show_options = bpf_show_options,
@ -794,33 +625,23 @@ const struct super_operations bpf_super_ops = {
};
enum {
OPT_UID,
OPT_GID,
OPT_MODE,
OPT_DELEGATE_CMDS,
OPT_DELEGATE_MAPS,
OPT_DELEGATE_PROGS,
OPT_DELEGATE_ATTACHS,
};
static const struct fs_parameter_spec bpf_fs_parameters[] = {
fsparam_u32 ("uid", OPT_UID),
fsparam_u32 ("gid", OPT_GID),
fsparam_u32oct ("mode", OPT_MODE),
fsparam_string ("delegate_cmds", OPT_DELEGATE_CMDS),
fsparam_string ("delegate_maps", OPT_DELEGATE_MAPS),
fsparam_string ("delegate_progs", OPT_DELEGATE_PROGS),
fsparam_string ("delegate_attachs", OPT_DELEGATE_ATTACHS),
{}
};
struct bpf_mount_opts {
umode_t mode;
};
static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
struct bpf_mount_opts *opts = fc->s_fs_info;
struct bpf_mount_opts *opts = fc->fs_private;
struct fs_parse_result result;
kuid_t uid;
kgid_t gid;
int opt, err;
int opt;
opt = fs_parse(fc, bpf_fs_parameters, param, &result);
if (opt < 0) {
@ -841,104 +662,12 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param)
}
switch (opt) {
case OPT_UID:
uid = make_kuid(current_user_ns(), result.uint_32);
if (!uid_valid(uid))
goto bad_value;
/*
* The requested uid must be representable in the
* filesystem's idmapping.
*/
if (!kuid_has_mapping(fc->user_ns, uid))
goto bad_value;
opts->uid = uid;
break;
case OPT_GID:
gid = make_kgid(current_user_ns(), result.uint_32);
if (!gid_valid(gid))
goto bad_value;
/*
* The requested gid must be representable in the
* filesystem's idmapping.
*/
if (!kgid_has_mapping(fc->user_ns, gid))
goto bad_value;
opts->gid = gid;
break;
case OPT_MODE:
opts->mode = result.uint_32 & S_IALLUGO;
break;
case OPT_DELEGATE_CMDS:
case OPT_DELEGATE_MAPS:
case OPT_DELEGATE_PROGS:
case OPT_DELEGATE_ATTACHS: {
struct bpffs_btf_enums info;
const struct btf_type *enum_t;
const char *enum_pfx;
u64 *delegate_msk, msk = 0;
char *p;
int val;
/* ignore errors, fallback to hex */
(void)find_bpffs_btf_enums(&info);
switch (opt) {
case OPT_DELEGATE_CMDS:
delegate_msk = &opts->delegate_cmds;
enum_t = info.cmd_t;
enum_pfx = "BPF_";
break;
case OPT_DELEGATE_MAPS:
delegate_msk = &opts->delegate_maps;
enum_t = info.map_t;
enum_pfx = "BPF_MAP_TYPE_";
break;
case OPT_DELEGATE_PROGS:
delegate_msk = &opts->delegate_progs;
enum_t = info.prog_t;
enum_pfx = "BPF_PROG_TYPE_";
break;
case OPT_DELEGATE_ATTACHS:
delegate_msk = &opts->delegate_attachs;
enum_t = info.attach_t;
enum_pfx = "BPF_";
break;
default:
return -EINVAL;
}
while ((p = strsep(&param->string, ":"))) {
if (strcmp(p, "any") == 0) {
msk |= ~0ULL;
} else if (find_btf_enum_const(info.btf, enum_t, enum_pfx, p, &val)) {
msk |= 1ULL << val;
} else {
err = kstrtou64(p, 0, &msk);
if (err)
return err;
}
}
/* Setting delegation mount options requires privileges */
if (msk && !capable(CAP_SYS_ADMIN))
return -EPERM;
*delegate_msk |= msk;
break;
}
default:
/* ignore unknown mount options */
break;
}
return 0;
bad_value:
return invalfc(fc, "Bad value for '%s'", param->key);
}
struct bpf_preload_ops *bpf_preload_ops;
@ -1010,14 +739,10 @@ out:
static int bpf_fill_super(struct super_block *sb, struct fs_context *fc)
{
static const struct tree_descr bpf_rfiles[] = { { "" } };
struct bpf_mount_opts *opts = sb->s_fs_info;
struct bpf_mount_opts *opts = fc->fs_private;
struct inode *inode;
int ret;
/* Mounting an instance of BPF FS requires privileges */
if (fc->user_ns != &init_user_ns && !capable(CAP_SYS_ADMIN))
return -EPERM;
ret = simple_fill_super(sb, BPF_FS_MAGIC, bpf_rfiles);
if (ret)
return ret;
@ -1025,8 +750,6 @@ static int bpf_fill_super(struct super_block *sb, struct fs_context *fc)
sb->s_op = &bpf_super_ops;
inode = sb->s_root->d_inode;
inode->i_uid = opts->uid;
inode->i_gid = opts->gid;
inode->i_op = &bpf_dir_iops;
inode->i_mode &= ~S_IALLUGO;
populate_bpffs(sb->s_root);
@ -1041,7 +764,7 @@ static int bpf_get_tree(struct fs_context *fc)
static void bpf_free_fc(struct fs_context *fc)
{
kfree(fc->s_fs_info);
kfree(fc->fs_private);
}
static const struct fs_context_operations bpf_context_ops = {
@ -1062,35 +785,18 @@ static int bpf_init_fs_context(struct fs_context *fc)
return -ENOMEM;
opts->mode = S_IRWXUGO;
opts->uid = current_fsuid();
opts->gid = current_fsgid();
/* start out with no BPF token delegation enabled */
opts->delegate_cmds = 0;
opts->delegate_maps = 0;
opts->delegate_progs = 0;
opts->delegate_attachs = 0;
fc->s_fs_info = opts;
fc->fs_private = opts;
fc->ops = &bpf_context_ops;
return 0;
}
static void bpf_kill_super(struct super_block *sb)
{
struct bpf_mount_opts *opts = sb->s_fs_info;
kill_litter_super(sb);
kfree(opts);
}
static struct file_system_type bpf_fs_type = {
.owner = THIS_MODULE,
.name = "bpf",
.init_fs_context = bpf_init_fs_context,
.parameters = bpf_fs_parameters,
.kill_sb = bpf_kill_super,
.fs_flags = FS_USERNS_MOUNT,
.kill_sb = kill_litter_super,
};
static int __init bpf_init(void)

215
kernel/bpf/syscall.c
View File

@ -1011,8 +1011,8 @@ int map_check_no_btf(const struct bpf_map *map,
return -ENOTSUPP;
}
static int map_check_btf(struct bpf_map *map, struct bpf_token *token,
const struct btf *btf, u32 btf_key_id, u32 btf_value_id)
static int map_check_btf(struct bpf_map *map, const struct btf *btf,
u32 btf_key_id, u32 btf_value_id)
{
const struct btf_type *key_type, *value_type;
u32 key_size, value_size;
@ -1040,7 +1040,7 @@ static int map_check_btf(struct bpf_map *map, struct bpf_token *token,
if (!IS_ERR_OR_NULL(map->record)) {
int i;
if (!bpf_token_capable(token, CAP_BPF)) {
if (!bpf_capable()) {
ret = -EPERM;
goto free_map_tab;
}
@ -1123,17 +1123,11 @@ free_map_tab:
return ret;
}
static bool bpf_net_capable(void)
{
return capable(CAP_NET_ADMIN) || capable(CAP_SYS_ADMIN);
}
#define BPF_MAP_CREATE_LAST_FIELD map_token_fd
#define BPF_MAP_CREATE_LAST_FIELD map_extra
/* called via syscall */
static int map_create(union bpf_attr *attr)
{
const struct bpf_map_ops *ops;
struct bpf_token *token = NULL;
int numa_node = bpf_map_attr_numa_node(attr);
u32 map_type = attr->map_type;
struct bpf_map *map;
@ -1184,32 +1178,14 @@ static int map_create(union bpf_attr *attr)
if (!ops->map_mem_usage)
return -EINVAL;
if (attr->map_token_fd) {
token = bpf_token_get_from_fd(attr->map_token_fd);
if (IS_ERR(token))
return PTR_ERR(token);
/* if current token doesn't grant map creation permissions,
* then we can't use this token, so ignore it and rely on
* system-wide capabilities checks
*/
if (!bpf_token_allow_cmd(token, BPF_MAP_CREATE) ||
!bpf_token_allow_map_type(token, attr->map_type)) {
bpf_token_put(token);
token = NULL;
}
}
err = -EPERM;
/* Intent here is for unprivileged_bpf_disabled to block BPF map
* creation for unprivileged users; other actions depend
* on fd availability and access to bpffs, so are dependent on
* object creation success. Even with unprivileged BPF disabled,
* capability checks are still carried out.
*/
if (sysctl_unprivileged_bpf_disabled && !bpf_token_capable(token, CAP_BPF))
goto put_token;
if (sysctl_unprivileged_bpf_disabled && !bpf_capable())
return -EPERM;
/* check privileged map type permissions */
switch (map_type) {
@ -1242,27 +1218,25 @@ static int map_create(union bpf_attr *attr)
case BPF_MAP_TYPE_LRU_PERCPU_HASH:
case BPF_MAP_TYPE_STRUCT_OPS:
case BPF_MAP_TYPE_CPUMAP:
if (!bpf_token_capable(token, CAP_BPF))
goto put_token;
if (!bpf_capable())
return -EPERM;
break;
case BPF_MAP_TYPE_SOCKMAP:
case BPF_MAP_TYPE_SOCKHASH:
case BPF_MAP_TYPE_DEVMAP:
case BPF_MAP_TYPE_DEVMAP_HASH:
case BPF_MAP_TYPE_XSKMAP:
if (!bpf_token_capable(token, CAP_NET_ADMIN))
goto put_token;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
break;
default:
WARN(1, "unsupported map type %d", map_type);
goto put_token;
return -EPERM;
}
map = ops->map_alloc(attr);
if (IS_ERR(map)) {
err = PTR_ERR(map);
goto put_token;
}
if (IS_ERR(map))
return PTR_ERR(map);
map->ops = ops;
map->map_type = map_type;
@ -1299,7 +1273,7 @@ static int map_create(union bpf_attr *attr)
map->btf = btf;
if (attr->btf_value_type_id) {
err = map_check_btf(map, token, btf, attr->btf_key_type_id,
err = map_check_btf(map, btf, attr->btf_key_type_id,
attr->btf_value_type_id);
if (err)
goto free_map;
@ -1311,16 +1285,15 @@ static int map_create(union bpf_attr *attr)
attr->btf_vmlinux_value_type_id;
}
err = security_bpf_map_create(map, attr, token);
err = security_bpf_map_alloc(map);
if (err)
goto free_map_sec;
goto free_map;
err = bpf_map_alloc_id(map);
if (err)
goto free_map_sec;
bpf_map_save_memcg(map);
bpf_token_put(token);
err = bpf_map_new_fd(map, f_flags);
if (err < 0) {
@ -1341,8 +1314,6 @@ free_map_sec:
free_map:
btf_put(map->btf);
map->ops->map_free(map);
put_token:
bpf_token_put(token);
return err;
}
@ -2173,7 +2144,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
kvfree(aux->func_info);
kfree(aux->func_info_aux);
free_uid(aux->user);
security_bpf_prog_free(aux->prog);
security_bpf_prog_free(aux);
bpf_prog_free(aux->prog);
}
@ -2619,15 +2590,13 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type)
}
/* last field in 'union bpf_attr' used by this command */
#define BPF_PROG_LOAD_LAST_FIELD prog_token_fd
#define BPF_PROG_LOAD_LAST_FIELD log_true_size
static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
{
enum bpf_prog_type type = attr->prog_type;
struct bpf_prog *prog, *dst_prog = NULL;
struct btf *attach_btf = NULL;
struct bpf_token *token = NULL;
bool bpf_cap;
int err;
char license[128];
@ -2644,31 +2613,10 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
BPF_F_TEST_REG_INVARIANTS))
return -EINVAL;
bpf_prog_load_fixup_attach_type(attr);
if (attr->prog_token_fd) {
token = bpf_token_get_from_fd(attr->prog_token_fd);
if (IS_ERR(token))
return PTR_ERR(token);
/* if current token doesn't grant prog loading permissions,
* then we can't use this token, so ignore it and rely on
* system-wide capabilities checks
*/
if (!bpf_token_allow_cmd(token, BPF_PROG_LOAD) ||
!bpf_token_allow_prog_type(token, attr->prog_type,
attr->expected_attach_type)) {
bpf_token_put(token);
token = NULL;
}
}
bpf_cap = bpf_token_capable(token, CAP_BPF);
err = -EPERM;
if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
(attr->prog_flags & BPF_F_ANY_ALIGNMENT) &&
!bpf_cap)
goto put_token;
!bpf_capable())
return -EPERM;
/* Intent here is for unprivileged_bpf_disabled to block BPF program
* creation for unprivileged users; other actions depend
@ -2677,23 +2625,21 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
* capability checks are still carried out for these
* and other operations.
*/
if (sysctl_unprivileged_bpf_disabled && !bpf_cap)
goto put_token;
if (sysctl_unprivileged_bpf_disabled && !bpf_capable())
return -EPERM;
if (attr->insn_cnt == 0 ||
attr->insn_cnt > (bpf_cap ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) {
err = -E2BIG;
goto put_token;
}
attr->insn_cnt > (bpf_capable() ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS))
return -E2BIG;
if (type != BPF_PROG_TYPE_SOCKET_FILTER &&
type != BPF_PROG_TYPE_CGROUP_SKB &&
!bpf_cap)
goto put_token;
!bpf_capable())
return -EPERM;
if (is_net_admin_prog_type(type) && !bpf_token_capable(token, CAP_NET_ADMIN))
goto put_token;
if (is_perfmon_prog_type(type) && !bpf_token_capable(token, CAP_PERFMON))
goto put_token;
if (is_net_admin_prog_type(type) && !capable(CAP_NET_ADMIN) && !capable(CAP_SYS_ADMIN))
return -EPERM;
if (is_perfmon_prog_type(type) && !perfmon_capable())
return -EPERM;
/* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog
* or btf, we need to check which one it is
@ -2703,33 +2649,27 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
if (IS_ERR(dst_prog)) {
dst_prog = NULL;
attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd);
if (IS_ERR(attach_btf)) {
err = -EINVAL;
goto put_token;
}
if (IS_ERR(attach_btf))
return -EINVAL;
if (!btf_is_kernel(attach_btf)) {
/* attaching through specifying bpf_prog's BTF
* objects directly might be supported eventually
*/
btf_put(attach_btf);
err = -ENOTSUPP;
goto put_token;
return -ENOTSUPP;
}
}
} else if (attr->attach_btf_id) {
/* fall back to vmlinux BTF, if BTF type ID is specified */
attach_btf = bpf_get_btf_vmlinux();
if (IS_ERR(attach_btf)) {
err = PTR_ERR(attach_btf);
goto put_token;
}
if (!attach_btf) {
err = -EINVAL;
goto put_token;
}
if (IS_ERR(attach_btf))
return PTR_ERR(attach_btf);
if (!attach_btf)
return -EINVAL;
btf_get(attach_btf);
}
bpf_prog_load_fixup_attach_type(attr);
if (bpf_prog_load_check_attach(type, attr->expected_attach_type,
attach_btf, attr->attach_btf_id,
dst_prog)) {
@ -2737,8 +2677,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
bpf_prog_put(dst_prog);
if (attach_btf)
btf_put(attach_btf);
err = -EINVAL;
goto put_token;
return -EINVAL;
}
/* plain bpf_prog allocation */
@ -2748,8 +2687,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
bpf_prog_put(dst_prog);
if (attach_btf)
btf_put(attach_btf);
err = -EINVAL;
goto put_token;
return -ENOMEM;
}
prog->expected_attach_type = attr->expected_attach_type;
@ -2760,9 +2698,9 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE;
prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS;
/* move token into prog->aux, reuse taken refcnt */
prog->aux->token = token;
token = NULL;
err = security_bpf_prog_alloc(prog->aux);
if (err)
goto free_prog;
prog->aux->user = get_current_user();
prog->len = attr->insn_cnt;
@ -2771,12 +2709,12 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
if (copy_from_bpfptr(prog->insns,
make_bpfptr(attr->insns, uattr.is_kernel),
bpf_prog_insn_size(prog)) != 0)
goto free_prog;
goto free_prog_sec;
/* copy eBPF program license from user space */
if (strncpy_from_bpfptr(license,
make_bpfptr(attr->license, uattr.is_kernel),
sizeof(license) - 1) < 0)
goto free_prog;
goto free_prog_sec;
license[sizeof(license) - 1] = 0;
/* eBPF programs must be GPL compatible to use GPL-ed functions */
@ -2790,29 +2728,25 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
if (bpf_prog_is_dev_bound(prog->aux)) {
err = bpf_prog_dev_bound_init(prog, attr);
if (err)
goto free_prog;
goto free_prog_sec;
}
if (type == BPF_PROG_TYPE_EXT && dst_prog &&
bpf_prog_is_dev_bound(dst_prog->aux)) {
err = bpf_prog_dev_bound_inherit(prog, dst_prog);
if (err)
goto free_prog;
goto free_prog_sec;
}
/* find program type: socket_filter vs tracing_filter */
err = find_prog_type(type, prog);
if (err < 0)
goto free_prog;
goto free_prog_sec;
prog->aux->load_time = ktime_get_boottime_ns();
err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name,
sizeof(attr->prog_name));
if (err < 0)
goto free_prog;
err = security_bpf_prog_load(prog, attr, token);
if (err)
goto free_prog_sec;
/* run eBPF verifier */
@ -2858,16 +2792,13 @@ free_used_maps:
*/
__bpf_prog_put_noref(prog, prog->aux->real_func_cnt);
return err;
free_prog_sec:
security_bpf_prog_free(prog);
free_prog:
free_uid(prog->aux->user);
security_bpf_prog_free(prog->aux);
free_prog:
if (prog->aux->attach_btf)
btf_put(prog->aux->attach_btf);
bpf_prog_free(prog);
put_token:
bpf_token_put(token);
return err;
}
@ -3857,7 +3788,7 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
case BPF_PROG_TYPE_SK_LOOKUP:
return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
case BPF_PROG_TYPE_CGROUP_SKB:
if (!bpf_token_capable(prog->aux->token, CAP_NET_ADMIN))
if (!capable(CAP_NET_ADMIN))
/* cg-skb progs can be loaded by unpriv user.
* check permissions at attach time.
*/
@ -4060,7 +3991,7 @@ static int bpf_prog_detach(const union bpf_attr *attr)
static int bpf_prog_query(const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
if (!bpf_net_capable())
if (!capable(CAP_NET_ADMIN))
return -EPERM;
if (CHECK_ATTR(BPF_PROG_QUERY))
return -EINVAL;
@ -4828,31 +4759,15 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
return err;
}
#define BPF_BTF_LOAD_LAST_FIELD btf_token_fd
#define BPF_BTF_LOAD_LAST_FIELD btf_log_true_size
static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size)
{
struct bpf_token *token = NULL;
if (CHECK_ATTR(BPF_BTF_LOAD))
return -EINVAL;
if (attr->btf_token_fd) {
token = bpf_token_get_from_fd(attr->btf_token_fd);
if (IS_ERR(token))
return PTR_ERR(token);
if (!bpf_token_allow_cmd(token, BPF_BTF_LOAD)) {
bpf_token_put(token);
token = NULL;
}
}
if (!bpf_token_capable(token, CAP_BPF)) {
bpf_token_put(token);
if (!bpf_capable())
return -EPERM;
}
bpf_token_put(token);
return btf_new_fd(attr, uattr, uattr_size);
}
@ -5470,20 +5385,6 @@ out_prog_put:
return ret;
}
#define BPF_TOKEN_CREATE_LAST_FIELD token_create.bpffs_fd
static int token_create(union bpf_attr *attr)
{
if (CHECK_ATTR(BPF_TOKEN_CREATE))
return -EINVAL;
/* no flags are supported yet */
if (attr->token_create.flags)
return -EINVAL;
return bpf_token_create(attr);
}
static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size)
{
union bpf_attr attr;
@ -5617,9 +5518,6 @@ static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size)
case BPF_PROG_BIND_MAP:
err = bpf_prog_bind_map(&attr);
break;
case BPF_TOKEN_CREATE:
err = token_create(&attr);
break;
default:
err = -EINVAL;
break;
@ -5726,7 +5624,7 @@ static const struct bpf_func_proto bpf_sys_bpf_proto = {
const struct bpf_func_proto * __weak
tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
return bpf_base_func_proto(func_id, prog);
return bpf_base_func_proto(func_id);
}
BPF_CALL_1(bpf_sys_close, u32, fd)
@ -5776,8 +5674,7 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
case BPF_FUNC_sys_bpf:
return !bpf_token_capable(prog->aux->token, CAP_PERFMON)
? NULL : &bpf_sys_bpf_proto;
return !perfmon_capable() ? NULL : &bpf_sys_bpf_proto;
case BPF_FUNC_btf_find_by_name_kind:
return &bpf_btf_find_by_name_kind_proto;
case BPF_FUNC_sys_close:

271
kernel/bpf/token.c
View File

@ -1,271 +0,0 @@
#include <linux/bpf.h>
#include <linux/vmalloc.h>
#include <linux/fdtable.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/idr.h>
#include <linux/namei.h>
#include <linux/user_namespace.h>
#include <linux/security.h>
bool bpf_token_capable(const struct bpf_token *token, int cap)
{
/* BPF token allows ns_capable() level of capabilities, but only if
* token's userns is *exactly* the same as current user's userns
*/
if (token && current_user_ns() == token->userns) {
if (ns_capable(token->userns, cap) ||
(cap != CAP_SYS_ADMIN && ns_capable(token->userns, CAP_SYS_ADMIN)))
return security_bpf_token_capable(token, cap) == 0;
}
/* otherwise fallback to capable() checks */
return capable(cap) || (cap != CAP_SYS_ADMIN && capable(CAP_SYS_ADMIN));
}
void bpf_token_inc(struct bpf_token *token)
{
atomic64_inc(&token->refcnt);
}
static void bpf_token_free(struct bpf_token *token)
{
security_bpf_token_free(token);
put_user_ns(token->userns);
kvfree(token);
}
static void bpf_token_put_deferred(struct work_struct *work)
{
struct bpf_token *token = container_of(work, struct bpf_token, work);
bpf_token_free(token);
}
void bpf_token_put(struct bpf_token *token)
{
if (!token)
return;
if (!atomic64_dec_and_test(&token->refcnt))
return;
INIT_WORK(&token->work, bpf_token_put_deferred);
schedule_work(&token->work);
}
static int bpf_token_release(struct inode *inode, struct file *filp)
{
struct bpf_token *token = filp->private_data;
bpf_token_put(token);
return 0;
}
static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp)
{
struct bpf_token *token = filp->private_data;
u64 mask;
BUILD_BUG_ON(__MAX_BPF_CMD >= 64);
mask = (1ULL << __MAX_BPF_CMD) - 1;
if ((token->allowed_cmds & mask) == mask)
seq_printf(m, "allowed_cmds:\tany\n");
else
seq_printf(m, "allowed_cmds:\t0x%llx\n", token->allowed_cmds);
BUILD_BUG_ON(__MAX_BPF_MAP_TYPE >= 64);
mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1;
if ((token->allowed_maps & mask) == mask)
seq_printf(m, "allowed_maps:\tany\n");
else
seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps);
BUILD_BUG_ON(__MAX_BPF_PROG_TYPE >= 64);
mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1;
if ((token->allowed_progs & mask) == mask)
seq_printf(m, "allowed_progs:\tany\n");
else
seq_printf(m, "allowed_progs:\t0x%llx\n", token->allowed_progs);
BUILD_BUG_ON(__MAX_BPF_ATTACH_TYPE >= 64);
mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1;
if ((token->allowed_attachs & mask) == mask)
seq_printf(m, "allowed_attachs:\tany\n");
else
seq_printf(m, "allowed_attachs:\t0x%llx\n", token->allowed_attachs);
}
#define BPF_TOKEN_INODE_NAME "bpf-token"
static const struct inode_operations bpf_token_iops = { };
static const struct file_operations bpf_token_fops = {
.release = bpf_token_release,
.show_fdinfo = bpf_token_show_fdinfo,
};
int bpf_token_create(union bpf_attr *attr)
{
struct bpf_mount_opts *mnt_opts;
struct bpf_token *token = NULL;
struct user_namespace *userns;
struct inode *inode;
struct file *file;
struct path path;
struct fd f;
umode_t mode;
int err, fd;
f = fdget(attr->token_create.bpffs_fd);
if (!f.file)
return -EBADF;
path = f.file->f_path;
path_get(&path);
fdput(f);
if (path.dentry != path.mnt->mnt_sb->s_root) {
err = -EINVAL;
goto out_path;
}
if (path.mnt->mnt_sb->s_op != &bpf_super_ops) {
err = -EINVAL;
goto out_path;
}
err = path_permission(&path, MAY_ACCESS);
if (err)
goto out_path;
userns = path.dentry->d_sb->s_user_ns;
/*
* Enforce that creators of BPF tokens are in the same user
* namespace as the BPF FS instance. This makes reasoning about
* permissions a lot easier and we can always relax this later.
*/
if (current_user_ns() != userns) {
err = -EPERM;
goto out_path;
}
if (!ns_capable(userns, CAP_BPF)) {
err = -EPERM;
goto out_path;
}
mnt_opts = path.dentry->d_sb->s_fs_info;
if (mnt_opts->delegate_cmds == 0 &&
mnt_opts->delegate_maps == 0 &&
mnt_opts->delegate_progs == 0 &&
mnt_opts->delegate_attachs == 0) {
err = -ENOENT; /* no BPF token delegation is set up */
goto out_path;
}
mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask());
inode = bpf_get_inode(path.mnt->mnt_sb, NULL, mode);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
goto out_path;
}
inode->i_op = &bpf_token_iops;
inode->i_fop = &bpf_token_fops;
clear_nlink(inode); /* make sure it is unlinked */
file = alloc_file_pseudo(inode, path.mnt, BPF_TOKEN_INODE_NAME, O_RDWR, &bpf_token_fops);
if (IS_ERR(file)) {
iput(inode);
err = PTR_ERR(file);
goto out_path;
}
token = kvzalloc(sizeof(*token), GFP_USER);
if (!token) {
err = -ENOMEM;
goto out_file;
}
atomic64_set(&token->refcnt, 1);
/* remember bpffs owning userns for future ns_capable() checks */
token->userns = get_user_ns(userns);
token->allowed_cmds = mnt_opts->delegate_cmds;
token->allowed_maps = mnt_opts->delegate_maps;
token->allowed_progs = mnt_opts->delegate_progs;
token->allowed_attachs = mnt_opts->delegate_attachs;
err = security_bpf_token_create(token, attr, &path);
if (err)
goto out_token;
fd = get_unused_fd_flags(O_CLOEXEC);
if (fd < 0) {
err = fd;
goto out_token;
}
file->private_data = token;
fd_install(fd, file);
path_put(&path);
return fd;
out_token:
bpf_token_free(token);
out_file:
fput(file);
out_path:
path_put(&path);
return err;
}
struct bpf_token *bpf_token_get_from_fd(u32 ufd)
{
struct fd f = fdget(ufd);
struct bpf_token *token;
if (!f.file)
return ERR_PTR(-EBADF);
if (f.file->f_op != &bpf_token_fops) {
fdput(f);
return ERR_PTR(-EINVAL);
}
token = f.file->private_data;
bpf_token_inc(token);
fdput(f);
return token;
}
bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd)
{
/* BPF token can be used only within exactly the same userns in which
* it was created
*/
if (!token || current_user_ns() != token->userns)
return false;
if (!(token->allowed_cmds & (1ULL << cmd)))
return false;
return security_bpf_token_cmd(token, cmd) == 0;
}
bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type)
{
if (!token || type >= __MAX_BPF_MAP_TYPE)
return false;
return token->allowed_maps & (1ULL << type);
}
bool bpf_token_allow_prog_type(const struct bpf_token *token,
enum bpf_prog_type prog_type,
enum bpf_attach_type attach_type)
{
if (!token || prog_type >= __MAX_BPF_PROG_TYPE || attach_type >= __MAX_BPF_ATTACH_TYPE)
return false;
return (token->allowed_progs & (1ULL << prog_type)) &&
(token->allowed_attachs & (1ULL << attach_type));
}

13
kernel/bpf/verifier.c
View File

@ -20594,12 +20594,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
env->prog = *prog;
env->ops = bpf_verifier_ops[env->prog->type];
env->fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel);
env->allow_ptr_leaks = bpf_allow_ptr_leaks(env->prog->aux->token);
env->allow_uninit_stack = bpf_allow_uninit_stack(env->prog->aux->token);
env->bypass_spec_v1 = bpf_bypass_spec_v1(env->prog->aux->token);
env->bypass_spec_v4 = bpf_bypass_spec_v4(env->prog->aux->token);
env->bpf_capable = is_priv = bpf_token_capable(env->prog->aux->token, CAP_BPF);
is_priv = bpf_capable();
bpf_get_btf_vmlinux();
@ -20631,6 +20626,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
if (attr->prog_flags & BPF_F_ANY_ALIGNMENT)
env->strict_alignment = false;
env->allow_ptr_leaks = bpf_allow_ptr_leaks();
env->allow_uninit_stack = bpf_allow_uninit_stack();
env->bypass_spec_v1 = bpf_bypass_spec_v1();
env->bypass_spec_v4 = bpf_bypass_spec_v4();
env->bpf_capable = bpf_capable();
if (is_priv)
env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ;
env->test_reg_invariants = attr->prog_flags & BPF_F_TEST_REG_INVARIANTS;

2
kernel/trace/bpf_trace.c
View File

@ -1629,7 +1629,7 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_trace_vprintk:
return bpf_get_trace_vprintk_proto();
default:
return bpf_base_func_proto(func_id, prog);
return bpf_base_func_proto(func_id);
}
}

38
net/core/filter.c
View File

@ -87,7 +87,7 @@
#include "dev.h"
static const struct bpf_func_proto *
bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog);
bpf_sk_base_func_proto(enum bpf_func_id func_id);
int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len)
{
@ -203,7 +203,7 @@ BPF_CALL_3(bpf_skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x)
return 0;
nla = (struct nlattr *) &skb->data[a];
if (nla->nla_len > skb->len - a)
if (!nla_ok(nla, skb->len - a))
return 0;
nla = nla_find_nested(nla, x);
@ -7862,7 +7862,7 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_ktime_get_coarse_ns:
return &bpf_ktime_get_coarse_ns_proto;
default:
return bpf_base_func_proto(func_id, prog);
return bpf_base_func_proto(func_id);
}
}
@ -7955,7 +7955,7 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return NULL;
}
default:
return bpf_sk_base_func_proto(func_id, prog);
return bpf_sk_base_func_proto(func_id);
}
}
@ -7974,7 +7974,7 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_perf_event_output:
return &bpf_skb_event_output_proto;
default:
return bpf_sk_base_func_proto(func_id, prog);
return bpf_sk_base_func_proto(func_id);
}
}
@ -8161,7 +8161,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
#endif
#endif
default:
return bpf_sk_base_func_proto(func_id, prog);
return bpf_sk_base_func_proto(func_id);
}
}
@ -8220,7 +8220,7 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
#endif
#endif
default:
return bpf_sk_base_func_proto(func_id, prog);
return bpf_sk_base_func_proto(func_id);
}
#if IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)
@ -8281,7 +8281,7 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_tcp_sock_proto;
#endif /* CONFIG_INET */
default:
return bpf_sk_base_func_proto(func_id, prog);
return bpf_sk_base_func_proto(func_id);
}
}
@ -8323,7 +8323,7 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_get_cgroup_classid_curr_proto;
#endif
default:
return bpf_sk_base_func_proto(func_id, prog);
return bpf_sk_base_func_proto(func_id);
}
}
@ -8367,7 +8367,7 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_skc_lookup_tcp_proto;
#endif
default:
return bpf_sk_base_func_proto(func_id, prog);
return bpf_sk_base_func_proto(func_id);
}
}
@ -8378,7 +8378,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_skb_load_bytes:
return &bpf_flow_dissector_load_bytes_proto;
default:
return bpf_sk_base_func_proto(func_id, prog);
return bpf_sk_base_func_proto(func_id);
}
}
@ -8405,7 +8405,7 @@ lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_skb_under_cgroup:
return &bpf_skb_under_cgroup_proto;
default:
return bpf_sk_base_func_proto(func_id, prog);
return bpf_sk_base_func_proto(func_id);
}
}
@ -8580,7 +8580,7 @@ static bool cg_skb_is_valid_access(int off, int size,
return false;
case bpf_ctx_range(struct __sk_buff, data):
case bpf_ctx_range(struct __sk_buff, data_end):
if (!bpf_token_capable(prog->aux->token, CAP_BPF))
if (!bpf_capable())
return false;
break;
}
@ -8592,7 +8592,7 @@ static bool cg_skb_is_valid_access(int off, int size,
case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]):
break;
case bpf_ctx_range(struct __sk_buff, tstamp):
if (!bpf_token_capable(prog->aux->token, CAP_BPF))
if (!bpf_capable())
return false;
break;
default:
@ -11236,7 +11236,7 @@ sk_reuseport_func_proto(enum bpf_func_id func_id,
case BPF_FUNC_ktime_get_coarse_ns:
return &bpf_ktime_get_coarse_ns_proto;
default:
return bpf_base_func_proto(func_id, prog);
return bpf_base_func_proto(func_id);
}
}
@ -11418,7 +11418,7 @@ sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_sk_release:
return &bpf_sk_release_proto;
default:
return bpf_sk_base_func_proto(func_id, prog);
return bpf_sk_base_func_proto(func_id);
}
}
@ -11752,7 +11752,7 @@ const struct bpf_func_proto bpf_sock_from_file_proto = {
};
static const struct bpf_func_proto *
bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
bpf_sk_base_func_proto(enum bpf_func_id func_id)
{
const struct bpf_func_proto *func;
@ -11781,10 +11781,10 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_ktime_get_coarse_ns:
return &bpf_ktime_get_coarse_ns_proto;
default:
return bpf_base_func_proto(func_id, prog);
return bpf_base_func_proto(func_id);
}
if (!bpf_token_capable(prog->aux->token, CAP_PERFMON))
if (!perfmon_capable())
return NULL;
return func;

2
net/ipv4/bpf_tcp_ca.c
View File

@ -191,7 +191,7 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id,
case BPF_FUNC_ktime_get_coarse_ns:
return &bpf_ktime_get_coarse_ns_proto;
default:
return bpf_base_func_proto(func_id, prog);
return bpf_base_func_proto(func_id);
}
}

2
net/netfilter/nf_bpf_link.c
View File

@ -314,7 +314,7 @@ static bool nf_is_valid_access(int off, int size, enum bpf_access_type type,
static const struct bpf_func_proto *
bpf_nf_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
return bpf_base_func_proto(func_id, prog);
return bpf_base_func_proto(func_id);
}
const struct bpf_verifier_ops netfilter_verifier_ops = {

101
security/security.c
View File

@ -5167,87 +5167,29 @@ int security_bpf_prog(struct bpf_prog *prog)
}
/**
* security_bpf_map_create() - Check if BPF map creation is allowed
* @map: BPF map object
* @attr: BPF syscall attributes used to create BPF map
* @token: BPF token used to grant user access
* security_bpf_map_alloc() - Allocate a bpf map LSM blob
* @map: bpf map
*
* Do a check when the kernel creates a new BPF map. This is also the
* point where LSM blob is allocated for LSMs that need them.
* Initialize the security field inside bpf map.
*
* Return: Returns 0 on success, error on failure.
*/
int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr,
struct bpf_token *token)
int security_bpf_map_alloc(struct bpf_map *map)
{
return call_int_hook(bpf_map_create, 0, map, attr, token);
return call_int_hook(bpf_map_alloc_security, 0, map);
}
/**
* security_bpf_prog_load() - Check if loading of BPF program is allowed
* @prog: BPF program object
* @attr: BPF syscall attributes used to create BPF program
* @token: BPF token used to grant user access to BPF subsystem
* security_bpf_prog_alloc() - Allocate a bpf program LSM blob
* @aux: bpf program aux info struct
*
* Perform an access control check when the kernel loads a BPF program and
* allocates associated BPF program object. This hook is also responsible for
* allocating any required LSM state for the BPF program.
* Initialize the security field inside bpf program.
*
* Return: Returns 0 on success, error on failure.
*/
int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr,
struct bpf_token *token)
int security_bpf_prog_alloc(struct bpf_prog_aux *aux)
{
return call_int_hook(bpf_prog_load, 0, prog, attr, token);
}
/**
* security_bpf_token_create() - Check if creating of BPF token is allowed
* @token: BPF token object
* @attr: BPF syscall attributes used to create BPF token
* @path: path pointing to BPF FS mount point from which BPF token is created
*
* Do a check when the kernel instantiates a new BPF token object from BPF FS
* instance. This is also the point where LSM blob can be allocated for LSMs.
*
* Return: Returns 0 on success, error on failure.
*/
int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr,
struct path *path)
{
return call_int_hook(bpf_token_create, 0, token, attr, path);
}
/**
* security_bpf_token_cmd() - Check if BPF token is allowed to delegate
* requested BPF syscall command
* @token: BPF token object
* @cmd: BPF syscall command requested to be delegated by BPF token
*
* Do a check when the kernel decides whether provided BPF token should allow
* delegation of requested BPF syscall command.
*
* Return: Returns 0 on success, error on failure.
*/
int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd)
{
return call_int_hook(bpf_token_cmd, 0, token, cmd);
}
/**
* security_bpf_token_capable() - Check if BPF token is allowed to delegate
* requested BPF-related capability
* @token: BPF token object
* @cap: capabilities requested to be delegated by BPF token
*
* Do a check when the kernel decides whether provided BPF token should allow
* delegation of requested BPF-related capabilities.
*
* Return: Returns 0 on success, error on failure.
*/
int security_bpf_token_capable(const struct bpf_token *token, int cap)
{
return call_int_hook(bpf_token_capable, 0, token, cap);
return call_int_hook(bpf_prog_alloc_security, 0, aux);
}
/**
@ -5258,29 +5200,18 @@ int security_bpf_token_capable(const struct bpf_token *token, int cap)
*/
void security_bpf_map_free(struct bpf_map *map)
{
call_void_hook(bpf_map_free, map);
call_void_hook(bpf_map_free_security, map);
}
/**
* security_bpf_prog_free() - Free a BPF program's LSM blob
* @prog: BPF program struct
* security_bpf_prog_free() - Free a bpf program's LSM blob
* @aux: bpf program aux info struct
*
* Clean up the security information stored inside BPF program.
* Clean up the security information stored inside bpf prog.
*/
void security_bpf_prog_free(struct bpf_prog *prog)
void security_bpf_prog_free(struct bpf_prog_aux *aux)
{
call_void_hook(bpf_prog_free, prog);
}
/**
* security_bpf_token_free() - Free a BPF token's LSM blob
* @token: BPF token struct
*
* Clean up the security information stored inside BPF token.
*/
void security_bpf_token_free(struct bpf_token *token)
{
call_void_hook(bpf_token_free, token);
call_void_hook(bpf_prog_free_security, aux);
}
#endif /* CONFIG_BPF_SYSCALL */

47
security/selinux/hooks.c
View File

@ -6783,8 +6783,7 @@ static int selinux_bpf_prog(struct bpf_prog *prog)
BPF__PROG_RUN, NULL);
}
static int selinux_bpf_map_create(struct bpf_map *map, union bpf_attr *attr,
struct bpf_token *token)
static int selinux_bpf_map_alloc(struct bpf_map *map)
{
struct bpf_security_struct *bpfsec;
@ -6806,8 +6805,7 @@ static void selinux_bpf_map_free(struct bpf_map *map)
kfree(bpfsec);
}
static int selinux_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr,
struct bpf_token *token)
static int selinux_bpf_prog_alloc(struct bpf_prog_aux *aux)
{
struct bpf_security_struct *bpfsec;
@ -6816,39 +6814,16 @@ static int selinux_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr,
return -ENOMEM;
bpfsec->sid = current_sid();
prog->aux->security = bpfsec;
aux->security = bpfsec;
return 0;
}
static void selinux_bpf_prog_free(struct bpf_prog *prog)
static void selinux_bpf_prog_free(struct bpf_prog_aux *aux)
{
struct bpf_security_struct *bpfsec = prog->aux->security;
struct bpf_security_struct *bpfsec = aux->security;
prog->aux->security = NULL;
kfree(bpfsec);
}
static int selinux_bpf_token_create(struct bpf_token *token, union bpf_attr *attr,
struct path *path)
{
struct bpf_security_struct *bpfsec;
bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL);
if (!bpfsec)
return -ENOMEM;
bpfsec->sid = current_sid();
token->security = bpfsec;
return 0;
}
static void selinux_bpf_token_free(struct bpf_token *token)
{
struct bpf_security_struct *bpfsec = token->security;
token->security = NULL;
aux->security = NULL;
kfree(bpfsec);
}
#endif
@ -7204,9 +7179,8 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = {
LSM_HOOK_INIT(bpf, selinux_bpf),
LSM_HOOK_INIT(bpf_map, selinux_bpf_map),
LSM_HOOK_INIT(bpf_prog, selinux_bpf_prog),
LSM_HOOK_INIT(bpf_map_free, selinux_bpf_map_free),
LSM_HOOK_INIT(bpf_prog_free, selinux_bpf_prog_free),
LSM_HOOK_INIT(bpf_token_free, selinux_bpf_token_free),
LSM_HOOK_INIT(bpf_map_free_security, selinux_bpf_map_free),
LSM_HOOK_INIT(bpf_prog_free_security, selinux_bpf_prog_free),
#endif
#ifdef CONFIG_PERF_EVENTS
@ -7263,9 +7237,8 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = {
LSM_HOOK_INIT(audit_rule_init, selinux_audit_rule_init),
#endif
#ifdef CONFIG_BPF_SYSCALL
LSM_HOOK_INIT(bpf_map_create, selinux_bpf_map_create),
LSM_HOOK_INIT(bpf_prog_load, selinux_bpf_prog_load),
LSM_HOOK_INIT(bpf_token_create, selinux_bpf_token_create),
LSM_HOOK_INIT(bpf_map_alloc_security, selinux_bpf_map_alloc),
LSM_HOOK_INIT(bpf_prog_alloc_security, selinux_bpf_prog_alloc),
#endif
#ifdef CONFIG_PERF_EVENTS
LSM_HOOK_INIT(perf_event_alloc, selinux_perf_event_alloc),

42
tools/include/uapi/linux/bpf.h
View File

@ -847,36 +847,6 @@ union bpf_iter_link_info {
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*
* BPF_TOKEN_CREATE
* Description
* Create BPF token with embedded information about what
* BPF-related functionality it allows:
* - a set of allowed bpf() syscall commands;
* - a set of allowed BPF map types to be created with
* BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed;
* - a set of allowed BPF program types and BPF program attach
* types to be loaded with BPF_PROG_LOAD command, if
* BPF_PROG_LOAD itself is allowed.
*
* BPF token is created (derived) from an instance of BPF FS,
* assuming it has necessary delegation mount options specified.
* This BPF token can be passed as an extra parameter to various
* bpf() syscall commands to grant BPF subsystem functionality to
* unprivileged processes.
*
* When created, BPF token is "associated" with the owning
* user namespace of BPF FS instance (super block) that it was
* derived from, and subsequent BPF operations performed with
* BPF token would be performing capabilities checks (i.e.,
* CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within
* that user namespace. Without BPF token, such capabilities
* have to be granted in init user namespace, making bpf()
* syscall incompatible with user namespace, for the most part.
*
* Return
* A new file descriptor (a nonnegative integer), or -1 if an
* error occurred (in which case, *errno* is set appropriately).
*
* NOTES
* eBPF objects (maps and programs) can be shared between processes.
*
@ -931,8 +901,6 @@ enum bpf_cmd {
BPF_ITER_CREATE,
BPF_LINK_DETACH,
BPF_PROG_BIND_MAP,
BPF_TOKEN_CREATE,
__MAX_BPF_CMD,
};
enum bpf_map_type {
@ -983,7 +951,6 @@ enum bpf_map_type {
BPF_MAP_TYPE_BLOOM_FILTER,
BPF_MAP_TYPE_USER_RINGBUF,
BPF_MAP_TYPE_CGRP_STORAGE,
__MAX_BPF_MAP_TYPE
};
/* Note that tracing related programs such as
@ -1028,7 +995,6 @@ enum bpf_prog_type {
BPF_PROG_TYPE_SK_LOOKUP,
BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */
BPF_PROG_TYPE_NETFILTER,
__MAX_BPF_PROG_TYPE
};
enum bpf_attach_type {
@ -1437,7 +1403,6 @@ union bpf_attr {
* to using 5 hash functions).
*/
__u64 map_extra;
__u32 map_token_fd;
};
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@ -1507,7 +1472,6 @@ union bpf_attr {
* truncated), or smaller (if log buffer wasn't filled completely).
*/
__u32 log_true_size;
__u32 prog_token_fd;
};
struct { /* anonymous struct used by BPF_OBJ_* commands */
@ -1620,7 +1584,6 @@ union bpf_attr {
* truncated), or smaller (if log buffer wasn't filled completely).
*/
__u32 btf_log_true_size;
__u32 btf_token_fd;
};
struct {
@ -1751,11 +1714,6 @@ union bpf_attr {
__u32 flags; /* extra flags */
} prog_bind_map;
struct { /* struct used by BPF_TOKEN_CREATE command */
__u32 flags;
__u32 bpffs_fd;
} token_create;
} __attribute__((aligned(8)));
/* The description below is an attempt at providing documentation to eBPF

2
tools/lib/bpf/Build
View File

@ -1,4 +1,4 @@
libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \
netlink.o bpf_prog_linfo.o libbpf_probes.o hashmap.o \
btf_dump.o ringbuf.o strset.o linker.o gen_loader.o relo_core.o \
usdt.o zip.o elf.o features.o
usdt.o zip.o elf.o

37
tools/lib/bpf/bpf.c
View File

@ -103,7 +103,7 @@ int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts)
* [0] https://lore.kernel.org/bpf/20201201215900.3569844-1-guro@fb.com/
* [1] d05512618056 ("bpf: Add bpf_ktime_get_coarse_ns helper")
*/
int probe_memcg_account(int token_fd)
int probe_memcg_account(void)
{
const size_t attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd);
struct bpf_insn insns[] = {
@ -120,7 +120,6 @@ int probe_memcg_account(int token_fd)
attr.insns = ptr_to_u64(insns);
attr.insn_cnt = insn_cnt;
attr.license = ptr_to_u64("GPL");
attr.prog_token_fd = token_fd;
prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, attr_sz);
if (prog_fd >= 0) {
@ -147,7 +146,7 @@ int bump_rlimit_memlock(void)
struct rlimit rlim;
/* if kernel supports memcg-based accounting, skip bumping RLIMIT_MEMLOCK */
if (memlock_bumped || feat_supported(NULL, FEAT_MEMCG_ACCOUNT))
if (memlock_bumped || kernel_supports(NULL, FEAT_MEMCG_ACCOUNT))
return 0;
memlock_bumped = true;
@ -170,7 +169,7 @@ int bpf_map_create(enum bpf_map_type map_type,
__u32 max_entries,
const struct bpf_map_create_opts *opts)
{
const size_t attr_sz = offsetofend(union bpf_attr, map_token_fd);
const size_t attr_sz = offsetofend(union bpf_attr, map_extra);
union bpf_attr attr;
int fd;
@ -182,7 +181,7 @@ int bpf_map_create(enum bpf_map_type map_type,
return libbpf_err(-EINVAL);
attr.map_type = map_type;
if (map_name && feat_supported(NULL, FEAT_PROG_NAME))
if (map_name && kernel_supports(NULL, FEAT_PROG_NAME))
libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name));
attr.key_size = key_size;
attr.value_size = value_size;
@ -199,8 +198,6 @@ int bpf_map_create(enum bpf_map_type map_type,
attr.numa_node = OPTS_GET(opts, numa_node, 0);
attr.map_ifindex = OPTS_GET(opts, map_ifindex, 0);
attr.map_token_fd = OPTS_GET(opts, token_fd, 0);
fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, attr_sz);
return libbpf_err_errno(fd);
}
@ -235,7 +232,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
const struct bpf_insn *insns, size_t insn_cnt,
struct bpf_prog_load_opts *opts)
{
const size_t attr_sz = offsetofend(union bpf_attr, prog_token_fd);
const size_t attr_sz = offsetofend(union bpf_attr, log_true_size);
void *finfo = NULL, *linfo = NULL;
const char *func_info, *line_info;
__u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd;
@ -264,9 +261,8 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
attr.prog_flags = OPTS_GET(opts, prog_flags, 0);
attr.prog_ifindex = OPTS_GET(opts, prog_ifindex, 0);
attr.kern_version = OPTS_GET(opts, kern_version, 0);
attr.prog_token_fd = OPTS_GET(opts, token_fd, 0);
if (prog_name && feat_supported(NULL, FEAT_PROG_NAME))
if (prog_name && kernel_supports(NULL, FEAT_PROG_NAME))
libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name));
attr.license = ptr_to_u64(license);
@ -1186,7 +1182,7 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd)
int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts *opts)
{
const size_t attr_sz = offsetofend(union bpf_attr, btf_token_fd);
const size_t attr_sz = offsetofend(union bpf_attr, btf_log_true_size);
union bpf_attr attr;
char *log_buf;
size_t log_size;
@ -1211,8 +1207,6 @@ int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts
attr.btf = ptr_to_u64(btf_data);
attr.btf_size = btf_size;
attr.btf_token_fd = OPTS_GET(opts, token_fd, 0);
/* log_level == 0 and log_buf != NULL means "try loading without
* log_buf, but retry with log_buf and log_level=1 on error", which is
* consistent across low-level and high-level BTF and program loading
@ -1293,20 +1287,3 @@ int bpf_prog_bind_map(int prog_fd, int map_fd,
ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, attr_sz);
return libbpf_err_errno(ret);
}
int bpf_token_create(int bpffs_fd, struct bpf_token_create_opts *opts)
{
const size_t attr_sz = offsetofend(union bpf_attr, token_create);
union bpf_attr attr;
int fd;
if (!OPTS_VALID(opts, bpf_token_create_opts))
return libbpf_err(-EINVAL);
memset(&attr, 0, attr_sz);
attr.token_create.bpffs_fd = bpffs_fd;
attr.token_create.flags = OPTS_GET(opts, flags, 0);
fd = sys_bpf_fd(BPF_TOKEN_CREATE, &attr, attr_sz);
return libbpf_err_errno(fd);
}

35
tools/lib/bpf/bpf.h
View File

@ -51,11 +51,8 @@ struct bpf_map_create_opts {
__u32 numa_node;
__u32 map_ifindex;
__u32 token_fd;
size_t :0;
};
#define bpf_map_create_opts__last_field token_fd
#define bpf_map_create_opts__last_field map_ifindex
LIBBPF_API int bpf_map_create(enum bpf_map_type map_type,
const char *map_name,
@ -105,10 +102,9 @@ struct bpf_prog_load_opts {
* If kernel doesn't support this feature, log_size is left unchanged.
*/
__u32 log_true_size;
__u32 token_fd;
size_t :0;
};
#define bpf_prog_load_opts__last_field token_fd
#define bpf_prog_load_opts__last_field log_true_size
LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type,
const char *prog_name, const char *license,
@ -134,10 +130,9 @@ struct bpf_btf_load_opts {
* If kernel doesn't support this feature, log_size is left unchanged.
*/
__u32 log_true_size;
__u32 token_fd;
size_t :0;
};
#define bpf_btf_load_opts__last_field token_fd
#define bpf_btf_load_opts__last_field log_true_size
LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size,
struct bpf_btf_load_opts *opts);
@ -645,30 +640,6 @@ struct bpf_test_run_opts {
LIBBPF_API int bpf_prog_test_run_opts(int prog_fd,
struct bpf_test_run_opts *opts);
struct bpf_token_create_opts {
size_t sz; /* size of this struct for forward/backward compatibility */
__u32 flags;
size_t :0;
};
#define bpf_token_create_opts__last_field flags
/**
* @brief **bpf_token_create()** creates a new instance of BPF token derived
* from specified BPF FS mount point.
*
* BPF token created with this API can be passed to bpf() syscall for
* commands like BPF_PROG_LOAD, BPF_MAP_CREATE, etc.
*
* @param bpffs_fd FD for BPF FS instance from which to derive a BPF token
* instance.
* @param opts optional BPF token creation options, can be NULL
*
* @return BPF token FD > 0, on success; negative error code, otherwise (errno
* is also set to the error code)
*/
LIBBPF_API int bpf_token_create(int bpffs_fd,
struct bpf_token_create_opts *opts);
#ifdef __cplusplus
} /* extern "C" */
#endif

7
tools/lib/bpf/btf.c
View File

@ -1317,9 +1317,7 @@ struct btf *btf__parse_split(const char *path, struct btf *base_btf)
static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian);
int btf_load_into_kernel(struct btf *btf,
char *log_buf, size_t log_sz, __u32 log_level,
int token_fd)
int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level)
{
LIBBPF_OPTS(bpf_btf_load_opts, opts);
__u32 buf_sz = 0, raw_size;
@ -1369,7 +1367,6 @@ retry_load:
opts.log_level = log_level;
}
opts.token_fd = token_fd;
btf->fd = bpf_btf_load(raw_data, raw_size, &opts);
if (btf->fd < 0) {
/* time to turn on verbose mode and try again */
@ -1397,7 +1394,7 @@ done:
int btf__load_into_kernel(struct btf *btf)
{
return btf_load_into_kernel(btf, NULL, 0, 0, 0);
return btf_load_into_kernel(btf, NULL, 0, 0);
}
int btf__fd(const struct btf *btf)

2
tools/lib/bpf/elf.c
View File

@ -11,6 +11,8 @@
#include "libbpf_internal.h"
#include "str_error.h"
#define STRERR_BUFSIZE 128
/* A SHT_GNU_versym section holds 16-bit words. This bit is set if
* the symbol is hidden and can only be seen when referenced using an
* explicit version number. This is a GNU extension.

478
tools/lib/bpf/features.c
View File

@ -1,478 +0,0 @@
// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
#include <linux/kernel.h>
#include <linux/filter.h>
#include "bpf.h"
#include "libbpf.h"
#include "libbpf_common.h"
#include "libbpf_internal.h"
#include "str_error.h"
static inline __u64 ptr_to_u64(const void *ptr)
{
return (__u64)(unsigned long)ptr;
}
static int probe_fd(int fd)
{
if (fd >= 0)
close(fd);
return fd >= 0;
}
static int probe_kern_prog_name(int token_fd)
{
const size_t attr_sz = offsetofend(union bpf_attr, prog_name);
struct bpf_insn insns[] = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
};
union bpf_attr attr;
int ret;
memset(&attr, 0, attr_sz);
attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
attr.license = ptr_to_u64("GPL");
attr.insns = ptr_to_u64(insns);
attr.insn_cnt = (__u32)ARRAY_SIZE(insns);
attr.prog_token_fd = token_fd;
libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name));
/* make sure loading with name works */
ret = sys_bpf_prog_load(&attr, attr_sz, PROG_LOAD_ATTEMPTS);
return probe_fd(ret);
}
static int probe_kern_global_data(int token_fd)
{
char *cp, errmsg[STRERR_BUFSIZE];
struct bpf_insn insns[] = {
BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16),
BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
};
LIBBPF_OPTS(bpf_map_create_opts, map_opts, .token_fd = token_fd);
LIBBPF_OPTS(bpf_prog_load_opts, prog_opts, .token_fd = token_fd);
int ret, map, insn_cnt = ARRAY_SIZE(insns);
map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, &map_opts);
if (map < 0) {
ret = -errno;
cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n",
__func__, cp, -ret);
return ret;
}
insns[0].imm = map;
ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &prog_opts);
close(map);
return probe_fd(ret);
}
static int probe_kern_btf(int token_fd)
{
static const char strs[] = "\0int";
__u32 types[] = {
/* int */
BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs), token_fd));
}
static int probe_kern_btf_func(int token_fd)
{
static const char strs[] = "\0int\0x\0a";
/* void x(int a) {} */
__u32 types[] = {
/* int */
BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
/* FUNC_PROTO */ /* [2] */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0),
BTF_PARAM_ENC(7, 1),
/* FUNC x */ /* [3] */
BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs), token_fd));
}
static int probe_kern_btf_func_global(int token_fd)
{
static const char strs[] = "\0int\0x\0a";
/* static void x(int a) {} */
__u32 types[] = {
/* int */
BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
/* FUNC_PROTO */ /* [2] */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0),
BTF_PARAM_ENC(7, 1),
/* FUNC x BTF_FUNC_GLOBAL */ /* [3] */
BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs), token_fd));
}
static int probe_kern_btf_datasec(int token_fd)
{
static const char strs[] = "\0x\0.data";
/* static int a; */
__u32 types[] = {
/* int */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
/* VAR x */ /* [2] */
BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
BTF_VAR_STATIC,
/* DATASEC val */ /* [3] */
BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
BTF_VAR_SECINFO_ENC(2, 0, 4),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs), token_fd));
}
static int probe_kern_btf_float(int token_fd)
{
static const char strs[] = "\0float";
__u32 types[] = {
/* float */
BTF_TYPE_FLOAT_ENC(1, 4),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs), token_fd));
}
static int probe_kern_btf_decl_tag(int token_fd)
{
static const char strs[] = "\0tag";
__u32 types[] = {
/* int */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
/* VAR x */ /* [2] */
BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
BTF_VAR_STATIC,
/* attr */
BTF_TYPE_DECL_TAG_ENC(1, 2, -1),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs), token_fd));
}
static int probe_kern_btf_type_tag(int token_fd)
{
static const char strs[] = "\0tag";
__u32 types[] = {
/* int */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
/* attr */
BTF_TYPE_TYPE_TAG_ENC(1, 1), /* [2] */
/* ptr */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2), /* [3] */
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs), token_fd));
}
static int probe_kern_array_mmap(int token_fd)
{
LIBBPF_OPTS(bpf_map_create_opts, opts,
.map_flags = BPF_F_MMAPABLE,
.token_fd = token_fd,
);
int fd;
fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts);
return probe_fd(fd);
}
static int probe_kern_exp_attach_type(int token_fd)
{
LIBBPF_OPTS(bpf_prog_load_opts, opts,
.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE,
.token_fd = token_fd,
);
struct bpf_insn insns[] = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
};
int fd, insn_cnt = ARRAY_SIZE(insns);
/* use any valid combination of program type and (optional)
* non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS)
* to see if kernel supports expected_attach_type field for
* BPF_PROG_LOAD command
*/
fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns, insn_cnt, &opts);
return probe_fd(fd);
}
static int probe_kern_probe_read_kernel(int token_fd)
{
LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = token_fd);
struct bpf_insn insns[] = {
BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), /* r1 = r10 (fp) */
BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), /* r1 += -8 */
BPF_MOV64_IMM(BPF_REG_2, 8), /* r2 = 8 */
BPF_MOV64_IMM(BPF_REG_3, 0), /* r3 = 0 */
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
};
int fd, insn_cnt = ARRAY_SIZE(insns);
fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts);
return probe_fd(fd);
}
static int probe_prog_bind_map(int token_fd)
{
char *cp, errmsg[STRERR_BUFSIZE];
struct bpf_insn insns[] = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
};
LIBBPF_OPTS(bpf_map_create_opts, map_opts, .token_fd = token_fd);
LIBBPF_OPTS(bpf_prog_load_opts, prog_opts, .token_fd = token_fd);
int ret, map, prog, insn_cnt = ARRAY_SIZE(insns);
map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, &map_opts);
if (map < 0) {
ret = -errno;
cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n",
__func__, cp, -ret);
return ret;
}
prog = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &prog_opts);
if (prog < 0) {
close(map);
return 0;
}
ret = bpf_prog_bind_map(prog, map, NULL);
close(map);
close(prog);
return ret >= 0;
}
static int probe_module_btf(int token_fd)
{
static const char strs[] = "\0int";
__u32 types[] = {
/* int */
BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),
};
struct bpf_btf_info info;
__u32 len = sizeof(info);
char name[16];
int fd, err;
fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs), token_fd);
if (fd < 0)
return 0; /* BTF not supported at all */
memset(&info, 0, sizeof(info));
info.name = ptr_to_u64(name);
info.name_len = sizeof(name);
/* check that BPF_OBJ_GET_INFO_BY_FD supports specifying name pointer;
* kernel's module BTF support coincides with support for
* name/name_len fields in struct bpf_btf_info.
*/
err = bpf_btf_get_info_by_fd(fd, &info, &len);
close(fd);
return !err;
}
static int probe_perf_link(int token_fd)
{
struct bpf_insn insns[] = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
};
LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = token_fd);
int prog_fd, link_fd, err;
prog_fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL",
insns, ARRAY_SIZE(insns), &opts);
if (prog_fd < 0)
return -errno;
/* use invalid perf_event FD to get EBADF, if link is supported;
* otherwise EINVAL should be returned
*/
link_fd = bpf_link_create(prog_fd, -1, BPF_PERF_EVENT, NULL);
err = -errno; /* close() can clobber errno */
if (link_fd >= 0)
close(link_fd);
close(prog_fd);
return link_fd < 0 && err == -EBADF;
}
static int probe_uprobe_multi_link(int token_fd)
{
LIBBPF_OPTS(bpf_prog_load_opts, load_opts,
.expected_attach_type = BPF_TRACE_UPROBE_MULTI,
.token_fd = token_fd,
);
LIBBPF_OPTS(bpf_link_create_opts, link_opts);
struct bpf_insn insns[] = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
};
int prog_fd, link_fd, err;
unsigned long offset = 0;
prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL",
insns, ARRAY_SIZE(insns), &load_opts);
if (prog_fd < 0)
return -errno;
/* Creating uprobe in '/' binary should fail with -EBADF. */
link_opts.uprobe_multi.path = "/";
link_opts.uprobe_multi.offsets = &offset;
link_opts.uprobe_multi.cnt = 1;
link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts);
err = -errno; /* close() can clobber errno */
if (link_fd >= 0)
close(link_fd);
close(prog_fd);
return link_fd < 0 && err == -EBADF;
}
static int probe_kern_bpf_cookie(int token_fd)
{
struct bpf_insn insns[] = {
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_attach_cookie),
BPF_EXIT_INSN(),
};
LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = token_fd);
int ret, insn_cnt = ARRAY_SIZE(insns);
ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts);
return probe_fd(ret);
}
static int probe_kern_btf_enum64(int token_fd)
{
static const char strs[] = "\0enum64";
__u32 types[] = {
BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs), token_fd));
}
typedef int (*feature_probe_fn)(int /* token_fd */);
static struct kern_feature_cache feature_cache;
static struct kern_feature_desc {
const char *desc;
feature_probe_fn probe;
} feature_probes[__FEAT_CNT] = {
[FEAT_PROG_NAME] = {
"BPF program name", probe_kern_prog_name,
},
[FEAT_GLOBAL_DATA] = {
"global variables", probe_kern_global_data,
},
[FEAT_BTF] = {
"minimal BTF", probe_kern_btf,
},
[FEAT_BTF_FUNC] = {
"BTF functions", probe_kern_btf_func,
},
[FEAT_BTF_GLOBAL_FUNC] = {
"BTF global function", probe_kern_btf_func_global,
},
[FEAT_BTF_DATASEC] = {
"BTF data section and variable", probe_kern_btf_datasec,
},
[FEAT_ARRAY_MMAP] = {
"ARRAY map mmap()", probe_kern_array_mmap,
},
[FEAT_EXP_ATTACH_TYPE] = {
"BPF_PROG_LOAD expected_attach_type attribute",
probe_kern_exp_attach_type,
},
[FEAT_PROBE_READ_KERN] = {
"bpf_probe_read_kernel() helper", probe_kern_probe_read_kernel,
},
[FEAT_PROG_BIND_MAP] = {
"BPF_PROG_BIND_MAP support", probe_prog_bind_map,
},
[FEAT_MODULE_BTF] = {
"module BTF support", probe_module_btf,
},
[FEAT_BTF_FLOAT] = {
"BTF_KIND_FLOAT support", probe_kern_btf_float,
},
[FEAT_PERF_LINK] = {
"BPF perf link support", probe_perf_link,
},
[FEAT_BTF_DECL_TAG] = {
"BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag,
},
[FEAT_BTF_TYPE_TAG] = {
"BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag,
},
[FEAT_MEMCG_ACCOUNT] = {
"memcg-based memory accounting", probe_memcg_account,
},
[FEAT_BPF_COOKIE] = {
"BPF cookie support", probe_kern_bpf_cookie,
},
[FEAT_BTF_ENUM64] = {
"BTF_KIND_ENUM64 support", probe_kern_btf_enum64,
},
[FEAT_SYSCALL_WRAPPER] = {
"Kernel using syscall wrapper", probe_kern_syscall_wrapper,
},
[FEAT_UPROBE_MULTI_LINK] = {
"BPF multi-uprobe link support", probe_uprobe_multi_link,
},
};
bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id)
{
struct kern_feature_desc *feat = &feature_probes[feat_id];
int ret;
/* assume global feature cache, unless custom one is provided */
if (!cache)
cache = &feature_cache;
if (READ_ONCE(cache->res[feat_id]) == FEAT_UNKNOWN) {
ret = feat->probe(cache->token_fd);
if (ret > 0) {
WRITE_ONCE(cache->res[feat_id], FEAT_SUPPORTED);
} else if (ret == 0) {
WRITE_ONCE(cache->res[feat_id], FEAT_MISSING);
} else {
pr_warn("Detection of kernel %s support failed: %d\n", feat->desc, ret);
WRITE_ONCE(cache->res[feat_id], FEAT_MISSING);
}
}
return READ_ONCE(cache->res[feat_id]) == FEAT_SUPPORTED;
}

573
tools/lib/bpf/libbpf.c
View File

@ -59,8 +59,6 @@
#define BPF_FS_MAGIC 0xcafe4a11
#endif
#define BPF_FS_DEFAULT_PATH "/sys/fs/bpf"
#define BPF_INSN_SZ (sizeof(struct bpf_insn))
/* vsprintf() in __base_pr() uses nonliteral format string. It may break
@ -695,10 +693,6 @@ struct bpf_object {
struct usdt_manager *usdt_man;
struct kern_feature_cache *feat_cache;
char *token_path;
int token_fd;
char path[];
};
@ -2198,7 +2192,7 @@ static int build_map_pin_path(struct bpf_map *map, const char *path)
int err;
if (!path)
path = BPF_FS_DEFAULT_PATH;
path = "/sys/fs/bpf";
err = pathname_concat(buf, sizeof(buf), path, bpf_map__name(map));
if (err)
@ -3285,7 +3279,7 @@ skip_exception_cb:
} else {
/* currently BPF_BTF_LOAD only supports log_level 1 */
err = btf_load_into_kernel(kern_btf, obj->log_buf, obj->log_size,
obj->log_level ? 1 : 0, obj->token_fd);
obj->log_level ? 1 : 0);
}
if (sanitize) {
if (!err) {
@ -4608,63 +4602,6 @@ int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries)
return 0;
}
static int bpf_object_prepare_token(struct bpf_object *obj)
{
const char *bpffs_path;
int bpffs_fd = -1, token_fd, err;
bool mandatory;
enum libbpf_print_level level;
/* token is already set up */
if (obj->token_fd > 0)
return 0;
/* token is explicitly prevented */
if (obj->token_fd < 0) {
pr_debug("object '%s': token is prevented, skipping...\n", obj->name);
/* reset to zero to avoid extra checks during map_create and prog_load steps */
obj->token_fd = 0;
return 0;
}
mandatory = obj->token_path != NULL;
level = mandatory ? LIBBPF_WARN : LIBBPF_DEBUG;
bpffs_path = obj->token_path ?: BPF_FS_DEFAULT_PATH;
bpffs_fd = open(bpffs_path, O_DIRECTORY, O_RDWR);
if (bpffs_fd < 0) {
err = -errno;
__pr(level, "object '%s': failed (%d) to open BPF FS mount at '%s'%s\n",
obj->name, err, bpffs_path,
mandatory ? "" : ", skipping optional step...");
return mandatory ? err : 0;
}
token_fd = bpf_token_create(bpffs_fd, 0);
close(bpffs_fd);
if (token_fd < 0) {
if (!mandatory && token_fd == -ENOENT) {
pr_debug("object '%s': BPF FS at '%s' doesn't have BPF token delegation set up, skipping...\n",
obj->name, bpffs_path);
return 0;
}
__pr(level, "object '%s': failed (%d) to create BPF token from '%s'%s\n",
obj->name, token_fd, bpffs_path,
mandatory ? "" : ", skipping optional step...");
return mandatory ? token_fd : 0;
}
obj->feat_cache = calloc(1, sizeof(*obj->feat_cache));
if (!obj->feat_cache) {
close(token_fd);
return -ENOMEM;
}
obj->token_fd = token_fd;
obj->feat_cache->token_fd = token_fd;
return 0;
}
static int
bpf_object__probe_loading(struct bpf_object *obj)
{
@ -4674,7 +4611,6 @@ bpf_object__probe_loading(struct bpf_object *obj)
BPF_EXIT_INSN(),
};
int ret, insn_cnt = ARRAY_SIZE(insns);
LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = obj->token_fd);
if (obj->gen_loader)
return 0;
@ -4684,9 +4620,9 @@ bpf_object__probe_loading(struct bpf_object *obj)
pr_warn("Failed to bump RLIMIT_MEMLOCK (err = %d), you might need to do it explicitly!\n", ret);
/* make sure basic loading works */
ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &opts);
ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL);
if (ret < 0)
ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts);
ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL);
if (ret < 0) {
ret = errno;
cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
@ -4701,18 +4637,462 @@ bpf_object__probe_loading(struct bpf_object *obj)
return 0;
}
static int probe_fd(int fd)
{
if (fd >= 0)
close(fd);
return fd >= 0;
}
static int probe_kern_prog_name(void)
{
const size_t attr_sz = offsetofend(union bpf_attr, prog_name);
struct bpf_insn insns[] = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
};
union bpf_attr attr;
int ret;
memset(&attr, 0, attr_sz);
attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
attr.license = ptr_to_u64("GPL");
attr.insns = ptr_to_u64(insns);
attr.insn_cnt = (__u32)ARRAY_SIZE(insns);
libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name));
/* make sure loading with name works */
ret = sys_bpf_prog_load(&attr, attr_sz, PROG_LOAD_ATTEMPTS);
return probe_fd(ret);
}
static int probe_kern_global_data(void)
{
char *cp, errmsg[STRERR_BUFSIZE];
struct bpf_insn insns[] = {
BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16),
BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
};
int ret, map, insn_cnt = ARRAY_SIZE(insns);
map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, NULL);
if (map < 0) {
ret = -errno;
cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n",
__func__, cp, -ret);
return ret;
}
insns[0].imm = map;
ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL);
close(map);
return probe_fd(ret);
}
static int probe_kern_btf(void)
{
static const char strs[] = "\0int";
__u32 types[] = {
/* int */
BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs)));
}
static int probe_kern_btf_func(void)
{
static const char strs[] = "\0int\0x\0a";
/* void x(int a) {} */
__u32 types[] = {
/* int */
BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
/* FUNC_PROTO */ /* [2] */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0),
BTF_PARAM_ENC(7, 1),
/* FUNC x */ /* [3] */
BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs)));
}
static int probe_kern_btf_func_global(void)
{
static const char strs[] = "\0int\0x\0a";
/* static void x(int a) {} */
__u32 types[] = {
/* int */
BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
/* FUNC_PROTO */ /* [2] */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0),
BTF_PARAM_ENC(7, 1),
/* FUNC x BTF_FUNC_GLOBAL */ /* [3] */
BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs)));
}
static int probe_kern_btf_datasec(void)
{
static const char strs[] = "\0x\0.data";
/* static int a; */
__u32 types[] = {
/* int */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
/* VAR x */ /* [2] */
BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
BTF_VAR_STATIC,
/* DATASEC val */ /* [3] */
BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
BTF_VAR_SECINFO_ENC(2, 0, 4),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs)));
}
static int probe_kern_btf_float(void)
{
static const char strs[] = "\0float";
__u32 types[] = {
/* float */
BTF_TYPE_FLOAT_ENC(1, 4),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs)));
}
static int probe_kern_btf_decl_tag(void)
{
static const char strs[] = "\0tag";
__u32 types[] = {
/* int */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
/* VAR x */ /* [2] */
BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
BTF_VAR_STATIC,
/* attr */
BTF_TYPE_DECL_TAG_ENC(1, 2, -1),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs)));
}
static int probe_kern_btf_type_tag(void)
{
static const char strs[] = "\0tag";
__u32 types[] = {
/* int */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
/* attr */
BTF_TYPE_TYPE_TAG_ENC(1, 1), /* [2] */
/* ptr */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2), /* [3] */
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs)));
}
static int probe_kern_array_mmap(void)
{
LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_MMAPABLE);
int fd;
fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts);
return probe_fd(fd);
}
static int probe_kern_exp_attach_type(void)
{
LIBBPF_OPTS(bpf_prog_load_opts, opts, .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE);
struct bpf_insn insns[] = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
};
int fd, insn_cnt = ARRAY_SIZE(insns);
/* use any valid combination of program type and (optional)
* non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS)
* to see if kernel supports expected_attach_type field for
* BPF_PROG_LOAD command
*/
fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns, insn_cnt, &opts);
return probe_fd(fd);
}
static int probe_kern_probe_read_kernel(void)
{
struct bpf_insn insns[] = {
BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), /* r1 = r10 (fp) */
BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), /* r1 += -8 */
BPF_MOV64_IMM(BPF_REG_2, 8), /* r2 = 8 */
BPF_MOV64_IMM(BPF_REG_3, 0), /* r3 = 0 */
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
};
int fd, insn_cnt = ARRAY_SIZE(insns);
fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL);
return probe_fd(fd);
}
static int probe_prog_bind_map(void)
{
char *cp, errmsg[STRERR_BUFSIZE];
struct bpf_insn insns[] = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
};
int ret, map, prog, insn_cnt = ARRAY_SIZE(insns);
map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, NULL);
if (map < 0) {
ret = -errno;
cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n",
__func__, cp, -ret);
return ret;
}
prog = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL);
if (prog < 0) {
close(map);
return 0;
}
ret = bpf_prog_bind_map(prog, map, NULL);
close(map);
close(prog);
return ret >= 0;
}
static int probe_module_btf(void)
{
static const char strs[] = "\0int";
__u32 types[] = {
/* int */
BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),
};
struct bpf_btf_info info;
__u32 len = sizeof(info);
char name[16];
int fd, err;
fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs));
if (fd < 0)
return 0; /* BTF not supported at all */
memset(&info, 0, sizeof(info));
info.name = ptr_to_u64(name);
info.name_len = sizeof(name);
/* check that BPF_OBJ_GET_INFO_BY_FD supports specifying name pointer;
* kernel's module BTF support coincides with support for
* name/name_len fields in struct bpf_btf_info.
*/
err = bpf_btf_get_info_by_fd(fd, &info, &len);
close(fd);
return !err;
}
static int probe_perf_link(void)
{
struct bpf_insn insns[] = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
};
int prog_fd, link_fd, err;
prog_fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL",
insns, ARRAY_SIZE(insns), NULL);
if (prog_fd < 0)
return -errno;
/* use invalid perf_event FD to get EBADF, if link is supported;
* otherwise EINVAL should be returned
*/
link_fd = bpf_link_create(prog_fd, -1, BPF_PERF_EVENT, NULL);
err = -errno; /* close() can clobber errno */
if (link_fd >= 0)
close(link_fd);
close(prog_fd);
return link_fd < 0 && err == -EBADF;
}
static int probe_uprobe_multi_link(void)
{
LIBBPF_OPTS(bpf_prog_load_opts, load_opts,
.expected_attach_type = BPF_TRACE_UPROBE_MULTI,
);
LIBBPF_OPTS(bpf_link_create_opts, link_opts);
struct bpf_insn insns[] = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
};
int prog_fd, link_fd, err;
unsigned long offset = 0;
prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL",
insns, ARRAY_SIZE(insns), &load_opts);
if (prog_fd < 0)
return -errno;
/* Creating uprobe in '/' binary should fail with -EBADF. */
link_opts.uprobe_multi.path = "/";
link_opts.uprobe_multi.offsets = &offset;
link_opts.uprobe_multi.cnt = 1;
link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts);
err = -errno; /* close() can clobber errno */
if (link_fd >= 0)
close(link_fd);
close(prog_fd);
return link_fd < 0 && err == -EBADF;
}
static int probe_kern_bpf_cookie(void)
{
struct bpf_insn insns[] = {
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_attach_cookie),
BPF_EXIT_INSN(),
};
int ret, insn_cnt = ARRAY_SIZE(insns);
ret = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", insns, insn_cnt, NULL);
return probe_fd(ret);
}
static int probe_kern_btf_enum64(void)
{
static const char strs[] = "\0enum64";
__u32 types[] = {
BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs)));
}
static int probe_kern_syscall_wrapper(void);
enum kern_feature_result {
FEAT_UNKNOWN = 0,
FEAT_SUPPORTED = 1,
FEAT_MISSING = 2,
};
typedef int (*feature_probe_fn)(void);
static struct kern_feature_desc {
const char *desc;
feature_probe_fn probe;
enum kern_feature_result res;
} feature_probes[__FEAT_CNT] = {
[FEAT_PROG_NAME] = {
"BPF program name", probe_kern_prog_name,
},
[FEAT_GLOBAL_DATA] = {
"global variables", probe_kern_global_data,
},
[FEAT_BTF] = {
"minimal BTF", probe_kern_btf,
},
[FEAT_BTF_FUNC] = {
"BTF functions", probe_kern_btf_func,
},
[FEAT_BTF_GLOBAL_FUNC] = {
"BTF global function", probe_kern_btf_func_global,
},
[FEAT_BTF_DATASEC] = {
"BTF data section and variable", probe_kern_btf_datasec,
},
[FEAT_ARRAY_MMAP] = {
"ARRAY map mmap()", probe_kern_array_mmap,
},
[FEAT_EXP_ATTACH_TYPE] = {
"BPF_PROG_LOAD expected_attach_type attribute",
probe_kern_exp_attach_type,
},
[FEAT_PROBE_READ_KERN] = {
"bpf_probe_read_kernel() helper", probe_kern_probe_read_kernel,
},
[FEAT_PROG_BIND_MAP] = {
"BPF_PROG_BIND_MAP support", probe_prog_bind_map,
},
[FEAT_MODULE_BTF] = {
"module BTF support", probe_module_btf,
},
[FEAT_BTF_FLOAT] = {
"BTF_KIND_FLOAT support", probe_kern_btf_float,
},
[FEAT_PERF_LINK] = {
"BPF perf link support", probe_perf_link,
},
[FEAT_BTF_DECL_TAG] = {
"BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag,
},
[FEAT_BTF_TYPE_TAG] = {
"BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag,
},
[FEAT_MEMCG_ACCOUNT] = {
"memcg-based memory accounting", probe_memcg_account,
},
[FEAT_BPF_COOKIE] = {
"BPF cookie support", probe_kern_bpf_cookie,
},
[FEAT_BTF_ENUM64] = {
"BTF_KIND_ENUM64 support", probe_kern_btf_enum64,
},
[FEAT_SYSCALL_WRAPPER] = {
"Kernel using syscall wrapper", probe_kern_syscall_wrapper,
},
[FEAT_UPROBE_MULTI_LINK] = {
"BPF multi-uprobe link support", probe_uprobe_multi_link,
},
};
bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id)
{
struct kern_feature_desc *feat = &feature_probes[feat_id];
int ret;
if (obj && obj->gen_loader)
/* To generate loader program assume the latest kernel
* to avoid doing extra prog_load, map_create syscalls.
*/
return true;
if (obj->token_fd)
return feat_supported(obj->feat_cache, feat_id);
if (READ_ONCE(feat->res) == FEAT_UNKNOWN) {
ret = feat->probe();
if (ret > 0) {
WRITE_ONCE(feat->res, FEAT_SUPPORTED);
} else if (ret == 0) {
WRITE_ONCE(feat->res, FEAT_MISSING);
} else {
pr_warn("Detection of kernel %s support failed: %d\n", feat->desc, ret);
WRITE_ONCE(feat->res, FEAT_MISSING);
}
}
return feat_supported(NULL, feat_id);
return READ_ONCE(feat->res) == FEAT_SUPPORTED;
}
static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd)
@ -4831,7 +5211,6 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
create_attr.map_flags = def->map_flags;
create_attr.numa_node = map->numa_node;
create_attr.map_extra = map->map_extra;
create_attr.token_fd = obj->token_fd;
if (bpf_map__is_struct_ops(map))
create_attr.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id;
@ -6667,7 +7046,6 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog
load_attr.attach_btf_id = prog->attach_btf_id;
load_attr.kern_version = kern_version;
load_attr.prog_ifindex = prog->prog_ifindex;
load_attr.token_fd = obj->token_fd;
/* specify func_info/line_info only if kernel supports them */
btf_fd = bpf_object__btf_fd(obj);
@ -7129,10 +7507,10 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object
static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, size_t obj_buf_sz,
const struct bpf_object_open_opts *opts)
{
const char *obj_name, *kconfig, *btf_tmp_path, *token_path;
const char *obj_name, *kconfig, *btf_tmp_path;
struct bpf_object *obj;
char tmp_name[64];
int err, token_fd;
int err;
char *log_buf;
size_t log_size;
__u32 log_level;
@ -7166,28 +7544,6 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf,
if (log_size && !log_buf)
return ERR_PTR(-EINVAL);
token_path = OPTS_GET(opts, bpf_token_path, NULL);
token_fd = OPTS_GET(opts, bpf_token_fd, -1);
/* non-empty token path can't be combined with invalid token FD */
if (token_path && token_path[0] != '\0' && token_fd < 0)
return ERR_PTR(-EINVAL);
/* empty token path can't be combined with valid token FD */
if (token_path && token_path[0] == '\0' && token_fd > 0)
return ERR_PTR(-EINVAL);
/* if user didn't specify bpf_token_path/bpf_token_fd explicitly,
* check if LIBBPF_BPF_TOKEN_PATH envvar was set and treat it as
* bpf_token_path option
*/
if (token_fd == 0 && !token_path)
token_path = getenv("LIBBPF_BPF_TOKEN_PATH");
/* empty token_path is equivalent to invalid token_fd */
if (token_path && token_path[0] == '\0') {
token_path = NULL;
token_fd = -1;
}
if (token_path && strlen(token_path) >= PATH_MAX)
return ERR_PTR(-ENAMETOOLONG);
obj = bpf_object__new(path, obj_buf, obj_buf_sz, obj_name);
if (IS_ERR(obj))
return obj;
@ -7196,19 +7552,6 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf,
obj->log_size = log_size;
obj->log_level = log_level;
obj->token_fd = token_fd <= 0 ? token_fd : dup_good_fd(token_fd);
if (token_fd > 0 && obj->token_fd < 0) {
err = -errno;
goto out;
}
if (token_path) {
obj->token_path = strdup(token_path);
if (!obj->token_path) {
err = -ENOMEM;
goto out;
}
}
btf_tmp_path = OPTS_GET(opts, btf_custom_path, NULL);
if (btf_tmp_path) {
if (strlen(btf_tmp_path) >= PATH_MAX) {
@ -7719,8 +8062,7 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch
if (obj->gen_loader)
bpf_gen__init(obj->gen_loader, extra_log_level, obj->nr_programs, obj->nr_maps);
err = bpf_object_prepare_token(obj);
err = err ? : bpf_object__probe_loading(obj);
err = bpf_object__probe_loading(obj);
err = err ? : bpf_object__load_vmlinux_btf(obj, false);
err = err ? : bpf_object__resolve_externs(obj, obj->kconfig);
err = err ? : bpf_object__sanitize_and_load_btf(obj);
@ -8257,11 +8599,6 @@ void bpf_object__close(struct bpf_object *obj)
}
zfree(&obj->programs);
zfree(&obj->feat_cache);
zfree(&obj->token_path);
if (obj->token_fd > 0)
close(obj->token_fd);
free(obj);
}
@ -10275,7 +10612,7 @@ static const char *arch_specific_syscall_pfx(void)
#endif
}
int probe_kern_syscall_wrapper(int token_fd)
static int probe_kern_syscall_wrapper(void)
{
char syscall_name[64];
const char *ksys_pfx;

37
tools/lib/bpf/libbpf.h
View File

@ -177,45 +177,10 @@ struct bpf_object_open_opts {
* logs through its print callback.
*/
__u32 kernel_log_level;
/* FD of a BPF token instantiated by user through bpf_token_create()
* API. BPF object will keep dup()'ed FD internally, so passed token
* FD can be closed after BPF object/skeleton open step.
*
* Setting bpf_token_fd to negative value disables libbpf's automatic
* attempt to create BPF token from default BPF FS mount point
* (/sys/fs/bpf), in case this default behavior is undesirable.
*
* If bpf_token_path and bpf_token_fd are not specified, libbpf will
* consult LIBBPF_BPF_TOKEN_PATH environment variable. If set, it will
* be taken as a value of bpf_token_path option and will force libbpf
* to either create BPF token from provided custom BPF FS path, or
* will disable implicit BPF token creation, if envvar value is an
* empty string.
*
* bpf_token_path and bpf_token_fd are mutually exclusive and only one
* of those options should be set. Either of them overrides
* LIBBPF_BPF_TOKEN_PATH envvar.
*/
int bpf_token_fd;
/* Path to BPF FS mount point to derive BPF token from.
*
* Created BPF token will be used for all bpf() syscall operations
* that accept BPF token (e.g., map creation, BTF and program loads,
* etc) automatically within instantiated BPF object.
*
* Setting bpf_token_path option to empty string disables libbpf's
* automatic attempt to create BPF token from default BPF FS mount
* point (/sys/fs/bpf), in case this default behavior is undesirable.
*
* bpf_token_path and bpf_token_fd are mutually exclusive and only one
* of those options should be set. Either of them overrides
* LIBBPF_BPF_TOKEN_PATH envvar.
*/
const char *bpf_token_path;
size_t :0;
};
#define bpf_object_open_opts__last_field bpf_token_path
#define bpf_object_open_opts__last_field kernel_log_level
/**
* @brief **bpf_object__open()** creates a bpf_object by opening

1
tools/lib/bpf/libbpf.map
View File

@ -401,7 +401,6 @@ LIBBPF_1.3.0 {
bpf_program__attach_netkit;
bpf_program__attach_tcx;
bpf_program__attach_uprobe_multi;
bpf_token_create;
ring__avail_data_size;
ring__consume;
ring__consumer_pos;

36
tools/lib/bpf/libbpf_internal.h
View File

@ -360,32 +360,15 @@ enum kern_feature_id {
__FEAT_CNT,
};
enum kern_feature_result {
FEAT_UNKNOWN = 0,
FEAT_SUPPORTED = 1,
FEAT_MISSING = 2,
};
struct kern_feature_cache {
enum kern_feature_result res[__FEAT_CNT];
int token_fd;
};
bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id);
int probe_memcg_account(void);
bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id);
int probe_kern_syscall_wrapper(int token_fd);
int probe_memcg_account(int token_fd);
int bump_rlimit_memlock(void);
int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz);
int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz);
int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
const char *str_sec, size_t str_len,
int token_fd);
int btf_load_into_kernel(struct btf *btf,
char *log_buf, size_t log_sz, __u32 log_level,
int token_fd);
const char *str_sec, size_t str_len);
int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level);
struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf);
void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type,
@ -549,17 +532,6 @@ static inline bool is_ldimm64_insn(struct bpf_insn *insn)
return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
}
/* Unconditionally dup FD, ensuring it doesn't use [0, 2] range.
* Original FD is not closed or altered in any other way.
* Preserves original FD value, if it's invalid (negative).
*/
static inline int dup_good_fd(int fd)
{
if (fd < 0)
return fd;
return fcntl(fd, F_DUPFD_CLOEXEC, 3);
}
/* if fd is stdin, stdout, or stderr, dup to a fd greater than 2
* Takes ownership of the fd passed in, and closes it if calling
* fcntl(fd, F_DUPFD_CLOEXEC, 3).
@ -571,7 +543,7 @@ static inline int ensure_good_fd(int fd)
if (fd < 0)
return fd;
if (fd < 3) {
fd = dup_good_fd(fd);
fd = fcntl(fd, F_DUPFD_CLOEXEC, 3);
saved_errno = errno;
close(old_fd);
errno = saved_errno;

8
tools/lib/bpf/libbpf_probes.c
View File

@ -219,8 +219,7 @@ int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts)
}
int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
const char *str_sec, size_t str_len,
int token_fd)
const char *str_sec, size_t str_len)
{
struct btf_header hdr = {
.magic = BTF_MAGIC,
@ -230,7 +229,6 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
.str_off = types_len,
.str_len = str_len,
};
LIBBPF_OPTS(bpf_btf_load_opts, opts, .token_fd = token_fd);
int btf_fd, btf_len;
__u8 *raw_btf;
@ -243,7 +241,7 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
memcpy(raw_btf + hdr.hdr_len, raw_types, hdr.type_len);
memcpy(raw_btf + hdr.hdr_len + hdr.type_len, str_sec, hdr.str_len);
btf_fd = bpf_btf_load(raw_btf, btf_len, &opts);
btf_fd = bpf_btf_load(raw_btf, btf_len, NULL);
free(raw_btf);
return btf_fd;
@ -273,7 +271,7 @@ static int load_local_storage_btf(void)
};
return libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs), 0);
strs, sizeof(strs));
}
static int probe_map_create(enum bpf_map_type map_type)

3
tools/lib/bpf/str_error.h
View File

@ -2,8 +2,5 @@
#ifndef __LIBBPF_STR_ERROR_H
#define __LIBBPF_STR_ERROR_H
#define STRERR_BUFSIZE 128
char *libbpf_strerror_r(int err, char *dst, int len);
#endif /* __LIBBPF_STR_ERROR_H */

4
tools/testing/selftests/bpf/prog_tests/libbpf_probes.c
View File

@ -30,8 +30,6 @@ void test_libbpf_probe_prog_types(void)
if (prog_type == BPF_PROG_TYPE_UNSPEC)
continue;
if (strcmp(prog_type_name, "__MAX_BPF_PROG_TYPE") == 0)
continue;
if (!test__start_subtest(prog_type_name))
continue;
@ -70,8 +68,6 @@ void test_libbpf_probe_map_types(void)
if (map_type == BPF_MAP_TYPE_UNSPEC)
continue;
if (strcmp(map_type_name, "__MAX_BPF_MAP_TYPE") == 0)
continue;
if (!test__start_subtest(map_type_name))
continue;

6
tools/testing/selftests/bpf/prog_tests/libbpf_str.c
View File

@ -132,9 +132,6 @@ static void test_libbpf_bpf_map_type_str(void)
const char *map_type_str;
char buf[256];
if (map_type == __MAX_BPF_MAP_TYPE)
continue;
map_type_name = btf__str_by_offset(btf, e->name_off);
map_type_str = libbpf_bpf_map_type_str(map_type);
ASSERT_OK_PTR(map_type_str, map_type_name);
@ -189,9 +186,6 @@ static void test_libbpf_bpf_prog_type_str(void)
const char *prog_type_str;
char buf[256];
if (prog_type == __MAX_BPF_PROG_TYPE)
continue;
prog_type_name = btf__str_by_offset(btf, e->name_off);
prog_type_str = libbpf_bpf_prog_type_str(prog_type);
ASSERT_OK_PTR(prog_type_str, prog_type_name);

1031
tools/testing/selftests/bpf/prog_tests/token.c
View File

File diff suppressed because it is too large Load Diff

13
tools/testing/selftests/bpf/progs/priv_map.c
View File

@ -1,13 +0,0 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
#include "vmlinux.h"
#include <bpf/bpf_helpers.h>
char _license[] SEC("license") = "GPL";
struct {
__uint(type, BPF_MAP_TYPE_QUEUE);
__uint(max_entries, 1);
__type(value, __u32);
} priv_map SEC(".maps");

13
tools/testing/selftests/bpf/progs/priv_prog.c
View File

@ -1,13 +0,0 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
#include "vmlinux.h"
#include <bpf/bpf_helpers.h>
char _license[] SEC("license") = "GPL";
SEC("kprobe")
int kprobe_prog(void *ctx)
{
return 1;
}